diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 4e18d95e548f1680f27bac98b8f1fa206607e546..0152370bf2fcd1ca68f72d5eaf8030e8800b44a5 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -266,6 +266,38 @@ emit_br_bset(struct nfp_prog *nfp_prog, swreg src, u8 bit, u16 addr, u8 defer)
 	emit_br_bit_relo(nfp_prog, src, bit, addr, defer, true, RELO_BR_REL);
 }
 
+static void
+__emit_br_alu(struct nfp_prog *nfp_prog, u16 areg, u16 breg, u16 imm_hi,
+	      u8 defer, bool dst_lmextn, bool src_lmextn)
+{
+	u64 insn;
+
+	insn = OP_BR_ALU_BASE |
+		FIELD_PREP(OP_BR_ALU_A_SRC, areg) |
+		FIELD_PREP(OP_BR_ALU_B_SRC, breg) |
+		FIELD_PREP(OP_BR_ALU_DEFBR, defer) |
+		FIELD_PREP(OP_BR_ALU_IMM_HI, imm_hi) |
+		FIELD_PREP(OP_BR_ALU_SRC_LMEXTN, src_lmextn) |
+		FIELD_PREP(OP_BR_ALU_DST_LMEXTN, dst_lmextn);
+
+	nfp_prog_push(nfp_prog, insn);
+}
+
+static void emit_rtn(struct nfp_prog *nfp_prog, swreg base, u8 defer)
+{
+	struct nfp_insn_ur_regs reg;
+	int err;
+
+	err = swreg_to_unrestricted(reg_none(), base, reg_imm(0), &reg);
+	if (err) {
+		nfp_prog->error = err;
+		return;
+	}
+
+	__emit_br_alu(nfp_prog, reg.areg, reg.breg, 0, defer, reg.dst_lmextn,
+		      reg.src_lmextn);
+}
+
 static void
 __emit_immed(struct nfp_prog *nfp_prog, u16 areg, u16 breg, u16 imm_hi,
 	     enum immed_width width, bool invert,
@@ -1137,7 +1169,7 @@ mem_op_stack(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	     unsigned int size, unsigned int ptr_off, u8 gpr, u8 ptr_gpr,
 	     bool clr_gpr, lmem_step step)
 {
-	s32 off = nfp_prog->stack_depth + meta->insn.off + ptr_off;
+	s32 off = nfp_prog->stack_frame_depth + meta->insn.off + ptr_off;
 	bool first = true, last;
 	bool needs_inc = false;
 	swreg stack_off_reg;
@@ -1146,7 +1178,8 @@ mem_op_stack(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	bool lm3 = true;
 	int ret;
 
-	if (meta->ptr_not_const) {
+	if (meta->ptr_not_const ||
+	    meta->flags & FLAG_INSN_PTR_CALLER_STACK_FRAME) {
 		/* Use of the last encountered ptr_off is OK, they all have
 		 * the same alignment.  Depend on low bits of value being
 		 * discarded when written to LMaddr register.
@@ -1690,7 +1723,7 @@ map_call_stack_common(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	s64 lm_off;
 
 	/* We only have to reload LM0 if the key is not at start of stack */
-	lm_off = nfp_prog->stack_depth;
+	lm_off = nfp_prog->stack_frame_depth;
 	lm_off += meta->arg2.reg.var_off.value + meta->arg2.reg.off;
 	load_lm_ptr = meta->arg2.var_off || lm_off;
 
@@ -1803,10 +1836,10 @@ static int mov_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 		swreg stack_depth_reg;
 
 		stack_depth_reg = ur_load_imm_any(nfp_prog,
-						  nfp_prog->stack_depth,
+						  nfp_prog->stack_frame_depth,
 						  stack_imm(nfp_prog));
-		emit_alu(nfp_prog, reg_both(dst),
-			 stack_reg(nfp_prog), ALU_OP_ADD, stack_depth_reg);
+		emit_alu(nfp_prog, reg_both(dst), stack_reg(nfp_prog),
+			 ALU_OP_ADD, stack_depth_reg);
 		wrp_immed(nfp_prog, reg_both(dst + 1), 0);
 	} else {
 		wrp_reg_mov(nfp_prog, dst, src);
@@ -3076,7 +3109,93 @@ static int jne_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return wrp_test_reg(nfp_prog, meta, ALU_OP_XOR, BR_BNE);
 }
 
-static int call(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+static int
+bpf_to_bpf_call(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	u32 ret_tgt, stack_depth, offset_br;
+	swreg tmp_reg;
+
+	stack_depth = round_up(nfp_prog->stack_frame_depth, STACK_FRAME_ALIGN);
+	/* Space for saving the return address is accounted for by the callee,
+	 * so stack_depth can be zero for the main function.
+	 */
+	if (stack_depth) {
+		tmp_reg = ur_load_imm_any(nfp_prog, stack_depth,
+					  stack_imm(nfp_prog));
+		emit_alu(nfp_prog, stack_reg(nfp_prog),
+			 stack_reg(nfp_prog), ALU_OP_ADD, tmp_reg);
+		emit_csr_wr(nfp_prog, stack_reg(nfp_prog),
+			    NFP_CSR_ACT_LM_ADDR0);
+	}
+
+	/* Two cases for jumping to the callee:
+	 *
+	 * - If callee uses and needs to save R6~R9 then:
+	 *     1. Put the start offset of the callee into imm_b(). This will
+	 *        require a fixup step, as we do not necessarily know this
+	 *        address yet.
+	 *     2. Put the return address from the callee to the caller into
+	 *        register ret_reg().
+	 *     3. (After defer slots are consumed) Jump to the subroutine that
+	 *        pushes the registers to the stack.
+	 *   The subroutine acts as a trampoline, and returns to the address in
+	 *   imm_b(), i.e. jumps to the callee.
+	 *
+	 * - If callee does not need to save R6~R9 then just load return
+	 *   address to the caller in ret_reg(), and jump to the callee
+	 *   directly.
+	 *
+	 * Using ret_reg() to pass the return address to the callee is set here
+	 * as a convention. The callee can then push this address onto its
+	 * stack frame in its prologue. The advantages of passing the return
+	 * address through ret_reg(), instead of pushing it to the stack right
+	 * here, are the following:
+	 * - It looks cleaner.
+	 * - If the called function is called multiple time, we get a lower
+	 *   program size.
+	 * - We save two no-op instructions that should be added just before
+	 *   the emit_br() when stack depth is not null otherwise.
+	 * - If we ever find a register to hold the return address during whole
+	 *   execution of the callee, we will not have to push the return
+	 *   address to the stack for leaf functions.
+	 */
+	if (!meta->jmp_dst) {
+		pr_err("BUG: BPF-to-BPF call has no destination recorded\n");
+		return -ELOOP;
+	}
+	if (nfp_prog->subprog[meta->jmp_dst->subprog_idx].needs_reg_push) {
+		ret_tgt = nfp_prog_current_offset(nfp_prog) + 3;
+		emit_br_relo(nfp_prog, BR_UNC, BR_OFF_RELO, 2,
+			     RELO_BR_GO_CALL_PUSH_REGS);
+		offset_br = nfp_prog_current_offset(nfp_prog);
+		wrp_immed_relo(nfp_prog, imm_b(nfp_prog), 0, RELO_IMMED_REL);
+	} else {
+		ret_tgt = nfp_prog_current_offset(nfp_prog) + 2;
+		emit_br(nfp_prog, BR_UNC, meta->n + 1 + meta->insn.imm, 1);
+		offset_br = nfp_prog_current_offset(nfp_prog);
+	}
+	wrp_immed_relo(nfp_prog, ret_reg(nfp_prog), ret_tgt, RELO_IMMED_REL);
+
+	if (!nfp_prog_confirm_current_offset(nfp_prog, ret_tgt))
+		return -EINVAL;
+
+	if (stack_depth) {
+		tmp_reg = ur_load_imm_any(nfp_prog, stack_depth,
+					  stack_imm(nfp_prog));
+		emit_alu(nfp_prog, stack_reg(nfp_prog),
+			 stack_reg(nfp_prog), ALU_OP_SUB, tmp_reg);
+		emit_csr_wr(nfp_prog, stack_reg(nfp_prog),
+			    NFP_CSR_ACT_LM_ADDR0);
+		wrp_nops(nfp_prog, 3);
+	}
+
+	meta->num_insns_after_br = nfp_prog_current_offset(nfp_prog);
+	meta->num_insns_after_br -= offset_br;
+
+	return 0;
+}
+
+static int helper_call(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	switch (meta->insn.imm) {
 	case BPF_FUNC_xdp_adjust_head:
@@ -3097,6 +3216,19 @@ static int call(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	}
 }
 
+static int call(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	if (is_mbpf_pseudo_call(meta))
+		return bpf_to_bpf_call(nfp_prog, meta);
+	else
+		return helper_call(nfp_prog, meta);
+}
+
+static bool nfp_is_main_function(struct nfp_insn_meta *meta)
+{
+	return meta->subprog_idx == 0;
+}
+
 static int goto_out(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	emit_br_relo(nfp_prog, BR_UNC, BR_OFF_RELO, 0, RELO_BR_GO_OUT);
@@ -3104,6 +3236,39 @@ static int goto_out(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int
+nfp_subprog_epilogue(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	if (nfp_prog->subprog[meta->subprog_idx].needs_reg_push) {
+		/* Pop R6~R9 to the stack via related subroutine.
+		 * We loaded the return address to the caller into ret_reg().
+		 * This means that the subroutine does not come back here, we
+		 * make it jump back to the subprogram caller directly!
+		 */
+		emit_br_relo(nfp_prog, BR_UNC, BR_OFF_RELO, 1,
+			     RELO_BR_GO_CALL_POP_REGS);
+		/* Pop return address from the stack. */
+		wrp_mov(nfp_prog, ret_reg(nfp_prog), reg_lm(0, 0));
+	} else {
+		/* Pop return address from the stack. */
+		wrp_mov(nfp_prog, ret_reg(nfp_prog), reg_lm(0, 0));
+		/* Jump back to caller if no callee-saved registers were used
+		 * by the subprogram.
+		 */
+		emit_rtn(nfp_prog, ret_reg(nfp_prog), 0);
+	}
+
+	return 0;
+}
+
+static int jmp_exit(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	if (nfp_is_main_function(meta))
+		return goto_out(nfp_prog, meta);
+	else
+		return nfp_subprog_epilogue(nfp_prog, meta);
+}
+
 static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU64 | BPF_MOV | BPF_X] =	mov_reg64,
 	[BPF_ALU64 | BPF_MOV | BPF_K] =	mov_imm64,
@@ -3192,36 +3357,66 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_JMP | BPF_JSET | BPF_X] =	jset_reg,
 	[BPF_JMP | BPF_JNE | BPF_X] =	jne_reg,
 	[BPF_JMP | BPF_CALL] =		call,
-	[BPF_JMP | BPF_EXIT] =		goto_out,
+	[BPF_JMP | BPF_EXIT] =		jmp_exit,
 };
 
 /* --- Assembler logic --- */
+static int
+nfp_fixup_immed_relo(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		     struct nfp_insn_meta *jmp_dst, u32 br_idx)
+{
+	if (immed_get_value(nfp_prog->prog[br_idx + 1])) {
+		pr_err("BUG: failed to fix up callee register saving\n");
+		return -EINVAL;
+	}
+
+	immed_set_value(&nfp_prog->prog[br_idx + 1], jmp_dst->off);
+
+	return 0;
+}
+
 static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 {
 	struct nfp_insn_meta *meta, *jmp_dst;
 	u32 idx, br_idx;
+	int err;
 
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
 		if (meta->skip)
 			continue;
-		if (meta->insn.code == (BPF_JMP | BPF_CALL))
-			continue;
 		if (BPF_CLASS(meta->insn.code) != BPF_JMP)
 			continue;
+		if (meta->insn.code == (BPF_JMP | BPF_EXIT) &&
+		    !nfp_is_main_function(meta))
+			continue;
+		if (is_mbpf_helper_call(meta))
+			continue;
 
 		if (list_is_last(&meta->l, &nfp_prog->insns))
 			br_idx = nfp_prog->last_bpf_off;
 		else
 			br_idx = list_next_entry(meta, l)->off - 1;
 
+		/* For BPF-to-BPF function call, a stack adjustment sequence is
+		 * generated after the return instruction. Therefore, we must
+		 * withdraw the length of this sequence to have br_idx pointing
+		 * to where the "branch" NFP instruction is expected to be.
+		 */
+		if (is_mbpf_pseudo_call(meta))
+			br_idx -= meta->num_insns_after_br;
+
 		if (!nfp_is_br(nfp_prog->prog[br_idx])) {
 			pr_err("Fixup found block not ending in branch %d %02x %016llx!!\n",
 			       br_idx, meta->insn.code, nfp_prog->prog[br_idx]);
 			return -ELOOP;
 		}
+
+		if (meta->insn.code == (BPF_JMP | BPF_EXIT))
+			continue;
+
 		/* Leave special branches for later */
 		if (FIELD_GET(OP_RELO_TYPE, nfp_prog->prog[br_idx]) !=
-		    RELO_BR_REL)
+		    RELO_BR_REL && !is_mbpf_pseudo_call(meta))
 			continue;
 
 		if (!meta->jmp_dst) {
@@ -3236,6 +3431,18 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 			return -ELOOP;
 		}
 
+		if (is_mbpf_pseudo_call(meta) &&
+		    nfp_prog->subprog[jmp_dst->subprog_idx].needs_reg_push) {
+			err = nfp_fixup_immed_relo(nfp_prog, meta,
+						   jmp_dst, br_idx);
+			if (err)
+				return err;
+		}
+
+		if (FIELD_GET(OP_RELO_TYPE, nfp_prog->prog[br_idx]) !=
+		    RELO_BR_REL)
+			continue;
+
 		for (idx = meta->off; idx <= br_idx; idx++) {
 			if (!nfp_is_br(nfp_prog->prog[idx]))
 				continue;
@@ -3253,6 +3460,27 @@ static void nfp_intro(struct nfp_prog *nfp_prog)
 		 plen_reg(nfp_prog), ALU_OP_AND, pv_len(nfp_prog));
 }
 
+static void
+nfp_subprog_prologue(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	/* Save return address into the stack. */
+	wrp_mov(nfp_prog, reg_lm(0, 0), ret_reg(nfp_prog));
+}
+
+static void
+nfp_start_subprog(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	unsigned int depth = nfp_prog->subprog[meta->subprog_idx].stack_depth;
+
+	nfp_prog->stack_frame_depth = round_up(depth, 4);
+	nfp_subprog_prologue(nfp_prog, meta);
+}
+
+bool nfp_is_subprog_start(struct nfp_insn_meta *meta)
+{
+	return meta->flags & FLAG_INSN_IS_SUBPROG_START;
+}
+
 static void nfp_outro_tc_da(struct nfp_prog *nfp_prog)
 {
 	/* TC direct-action mode:
@@ -3343,6 +3571,67 @@ static void nfp_outro_xdp(struct nfp_prog *nfp_prog)
 	emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_b(2), SHF_SC_L_SHF, 16);
 }
 
+static bool nfp_prog_needs_callee_reg_save(struct nfp_prog *nfp_prog)
+{
+	unsigned int idx;
+
+	for (idx = 1; idx < nfp_prog->subprog_cnt; idx++)
+		if (nfp_prog->subprog[idx].needs_reg_push)
+			return true;
+
+	return false;
+}
+
+static void nfp_push_callee_registers(struct nfp_prog *nfp_prog)
+{
+	u8 reg;
+
+	/* Subroutine: Save all callee saved registers (R6 ~ R9).
+	 * imm_b() holds the return address.
+	 */
+	nfp_prog->tgt_call_push_regs = nfp_prog_current_offset(nfp_prog);
+	for (reg = BPF_REG_6; reg <= BPF_REG_9; reg++) {
+		u8 adj = (reg - BPF_REG_0) * 2;
+		u8 idx = (reg - BPF_REG_6) * 2;
+
+		/* The first slot in the stack frame is used to push the return
+		 * address in bpf_to_bpf_call(), start just after.
+		 */
+		wrp_mov(nfp_prog, reg_lm(0, 1 + idx), reg_b(adj));
+
+		if (reg == BPF_REG_8)
+			/* Prepare to jump back, last 3 insns use defer slots */
+			emit_rtn(nfp_prog, imm_b(nfp_prog), 3);
+
+		wrp_mov(nfp_prog, reg_lm(0, 1 + idx + 1), reg_b(adj + 1));
+	}
+}
+
+static void nfp_pop_callee_registers(struct nfp_prog *nfp_prog)
+{
+	u8 reg;
+
+	/* Subroutine: Restore all callee saved registers (R6 ~ R9).
+	 * ret_reg() holds the return address.
+	 */
+	nfp_prog->tgt_call_pop_regs = nfp_prog_current_offset(nfp_prog);
+	for (reg = BPF_REG_6; reg <= BPF_REG_9; reg++) {
+		u8 adj = (reg - BPF_REG_0) * 2;
+		u8 idx = (reg - BPF_REG_6) * 2;
+
+		/* The first slot in the stack frame holds the return address,
+		 * start popping just after that.
+		 */
+		wrp_mov(nfp_prog, reg_both(adj), reg_lm(0, 1 + idx));
+
+		if (reg == BPF_REG_8)
+			/* Prepare to jump back, last 3 insns use defer slots */
+			emit_rtn(nfp_prog, ret_reg(nfp_prog), 3);
+
+		wrp_mov(nfp_prog, reg_both(adj + 1), reg_lm(0, 1 + idx + 1));
+	}
+}
+
 static void nfp_outro(struct nfp_prog *nfp_prog)
 {
 	switch (nfp_prog->type) {
@@ -3355,13 +3644,23 @@ static void nfp_outro(struct nfp_prog *nfp_prog)
 	default:
 		WARN_ON(1);
 	}
+
+	if (!nfp_prog_needs_callee_reg_save(nfp_prog))
+		return;
+
+	nfp_push_callee_registers(nfp_prog);
+	nfp_pop_callee_registers(nfp_prog);
 }
 
 static int nfp_translate(struct nfp_prog *nfp_prog)
 {
 	struct nfp_insn_meta *meta;
+	unsigned int depth;
 	int err;
 
+	depth = nfp_prog->subprog[0].stack_depth;
+	nfp_prog->stack_frame_depth = round_up(depth, 4);
+
 	nfp_intro(nfp_prog);
 	if (nfp_prog->error)
 		return nfp_prog->error;
@@ -3371,6 +3670,12 @@ static int nfp_translate(struct nfp_prog *nfp_prog)
 
 		meta->off = nfp_prog_current_offset(nfp_prog);
 
+		if (nfp_is_subprog_start(meta)) {
+			nfp_start_subprog(nfp_prog, meta);
+			if (nfp_prog->error)
+				return nfp_prog->error;
+		}
+
 		if (meta->skip) {
 			nfp_prog->n_translated++;
 			continue;
@@ -4013,20 +4318,35 @@ void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt)
 
 	/* Another pass to record jump information. */
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
+		struct nfp_insn_meta *dst_meta;
 		u64 code = meta->insn.code;
+		unsigned int dst_idx;
+		bool pseudo_call;
+
+		if (BPF_CLASS(code) != BPF_JMP)
+			continue;
+		if (BPF_OP(code) == BPF_EXIT)
+			continue;
+		if (is_mbpf_helper_call(meta))
+			continue;
 
-		if (BPF_CLASS(code) == BPF_JMP && BPF_OP(code) != BPF_EXIT &&
-		    BPF_OP(code) != BPF_CALL) {
-			struct nfp_insn_meta *dst_meta;
-			unsigned short dst_indx;
+		/* If opcode is BPF_CALL at this point, this can only be a
+		 * BPF-to-BPF call (a.k.a pseudo call).
+		 */
+		pseudo_call = BPF_OP(code) == BPF_CALL;
 
-			dst_indx = meta->n + 1 + meta->insn.off;
-			dst_meta = nfp_bpf_goto_meta(nfp_prog, meta, dst_indx,
-						     cnt);
+		if (pseudo_call)
+			dst_idx = meta->n + 1 + meta->insn.imm;
+		else
+			dst_idx = meta->n + 1 + meta->insn.off;
 
-			meta->jmp_dst = dst_meta;
-			dst_meta->flags |= FLAG_INSN_IS_JUMP_DST;
-		}
+		dst_meta = nfp_bpf_goto_meta(nfp_prog, meta, dst_idx, cnt);
+
+		if (pseudo_call)
+			dst_meta->flags |= FLAG_INSN_IS_SUBPROG_START;
+
+		dst_meta->flags |= FLAG_INSN_IS_JUMP_DST;
+		meta->jmp_dst = dst_meta;
 	}
 }
 
@@ -4049,6 +4369,7 @@ void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv)
 	for (i = 0; i < nfp_prog->prog_len; i++) {
 		enum nfp_relo_type special;
 		u32 val;
+		u16 off;
 
 		special = FIELD_GET(OP_RELO_TYPE, prog[i]);
 		switch (special) {
@@ -4065,6 +4386,24 @@ void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv)
 			br_set_offset(&prog[i],
 				      nfp_prog->tgt_abort + bv->start_off);
 			break;
+		case RELO_BR_GO_CALL_PUSH_REGS:
+			if (!nfp_prog->tgt_call_push_regs) {
+				pr_err("BUG: failed to detect subprogram registers needs\n");
+				err = -EINVAL;
+				goto err_free_prog;
+			}
+			off = nfp_prog->tgt_call_push_regs + bv->start_off;
+			br_set_offset(&prog[i], off);
+			break;
+		case RELO_BR_GO_CALL_POP_REGS:
+			if (!nfp_prog->tgt_call_pop_regs) {
+				pr_err("BUG: failed to detect subprogram registers needs\n");
+				err = -EINVAL;
+				goto err_free_prog;
+			}
+			off = nfp_prog->tgt_call_pop_regs + bv->start_off;
+			br_set_offset(&prog[i], off);
+			break;
 		case RELO_BR_NEXT_PKT:
 			br_set_offset(&prog[i], bv->tgt_done);
 			break;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 2134045e14c36a88c51717b7f4b36f07bbaa5c83..c0a12996728d309219064003c57e6964b3de67ab 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -61,6 +61,8 @@ enum nfp_relo_type {
 	/* internal jumps to parts of the outro */
 	RELO_BR_GO_OUT,
 	RELO_BR_GO_ABORT,
+	RELO_BR_GO_CALL_PUSH_REGS,
+	RELO_BR_GO_CALL_POP_REGS,
 	/* external jumps to fixed addresses */
 	RELO_BR_NEXT_PKT,
 	RELO_BR_HELPER,
@@ -104,6 +106,7 @@ enum pkt_vec {
 #define imma_a(np)	reg_a(STATIC_REG_IMMA)
 #define imma_b(np)	reg_b(STATIC_REG_IMMA)
 #define imm_both(np)	reg_both(STATIC_REG_IMM)
+#define ret_reg(np)	imm_a(np)
 
 #define NFP_BPF_ABI_FLAGS	reg_imm(0)
 #define   NFP_BPF_ABI_FLAG_MARK	1
@@ -257,7 +260,9 @@ struct nfp_bpf_reg_state {
 	bool var_off;
 };
 
-#define FLAG_INSN_IS_JUMP_DST	BIT(0)
+#define FLAG_INSN_IS_JUMP_DST			BIT(0)
+#define FLAG_INSN_IS_SUBPROG_START		BIT(1)
+#define FLAG_INSN_PTR_CALLER_STACK_FRAME	BIT(2)
 
 /**
  * struct nfp_insn_meta - BPF instruction wrapper
@@ -274,6 +279,7 @@ struct nfp_bpf_reg_state {
  * @xadd_maybe_16bit: 16bit immediate is possible
  * @jmp_dst: destination info for jump instructions
  * @jump_neg_op: jump instruction has inverted immediate, use ADD instead of SUB
+ * @num_insns_after_br: number of insns following a branch jump, used for fixup
  * @func_id: function id for call instructions
  * @arg1: arg1 for call instructions
  * @arg2: arg2 for call instructions
@@ -284,6 +290,7 @@ struct nfp_bpf_reg_state {
  * @off: index of first generated machine instruction (in nfp_prog.prog)
  * @n: eBPF instruction number
  * @flags: eBPF instruction extra optimization flags
+ * @subprog_idx: index of subprogram to which the instruction belongs
  * @skip: skip this instruction (optimized out)
  * @double_cb: callback for second part of the instruction
  * @l: link on nfp_prog->insns list
@@ -309,6 +316,7 @@ struct nfp_insn_meta {
 		struct {
 			struct nfp_insn_meta *jmp_dst;
 			bool jump_neg_op;
+			u32 num_insns_after_br; /* only for BPF-to-BPF calls */
 		};
 		/* function calls */
 		struct {
@@ -330,6 +338,7 @@ struct nfp_insn_meta {
 	unsigned int off;
 	unsigned short n;
 	unsigned short flags;
+	unsigned short subprog_idx;
 	bool skip;
 	instr_cb_t double_cb;
 
@@ -418,6 +427,34 @@ static inline bool is_mbpf_div(const struct nfp_insn_meta *meta)
 	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_DIV;
 }
 
+static inline bool is_mbpf_helper_call(const struct nfp_insn_meta *meta)
+{
+	struct bpf_insn insn = meta->insn;
+
+	return insn.code == (BPF_JMP | BPF_CALL) &&
+		insn.src_reg != BPF_PSEUDO_CALL;
+}
+
+static inline bool is_mbpf_pseudo_call(const struct nfp_insn_meta *meta)
+{
+	struct bpf_insn insn = meta->insn;
+
+	return insn.code == (BPF_JMP | BPF_CALL) &&
+		insn.src_reg == BPF_PSEUDO_CALL;
+}
+
+#define STACK_FRAME_ALIGN 64
+
+/**
+ * struct nfp_bpf_subprog_info - nfp BPF sub-program (a.k.a. function) info
+ * @stack_depth:	maximum stack depth used by this sub-program
+ * @needs_reg_push:	whether sub-program uses callee-saved registers
+ */
+struct nfp_bpf_subprog_info {
+	u16 stack_depth;
+	u8 needs_reg_push : 1;
+};
+
 /**
  * struct nfp_prog - nfp BPF program
  * @bpf: backpointer to the bpf app priv structure
@@ -429,12 +466,16 @@ static inline bool is_mbpf_div(const struct nfp_insn_meta *meta)
  * @last_bpf_off: address of the last instruction translated from BPF
  * @tgt_out: jump target for normal exit
  * @tgt_abort: jump target for abort (e.g. access outside of packet buffer)
+ * @tgt_call_push_regs: jump target for subroutine for saving R6~R9 to stack
+ * @tgt_call_pop_regs: jump target for subroutine used for restoring R6~R9
  * @n_translated: number of successfully translated instructions (for errors)
  * @error: error code if something went wrong
- * @stack_depth: max stack depth from the verifier
+ * @stack_frame_depth: max stack depth for current frame
  * @adjust_head_location: if program has single adjust head call - the insn no.
  * @map_records_cnt: the number of map pointers recorded for this prog
+ * @subprog_cnt: number of sub-programs, including main function
  * @map_records: the map record pointers from bpf->maps_neutral
+ * @subprog: pointer to an array of objects holding info about sub-programs
  * @insns: list of BPF instruction wrappers (struct nfp_insn_meta)
  */
 struct nfp_prog {
@@ -451,15 +492,19 @@ struct nfp_prog {
 	unsigned int last_bpf_off;
 	unsigned int tgt_out;
 	unsigned int tgt_abort;
+	unsigned int tgt_call_push_regs;
+	unsigned int tgt_call_pop_regs;
 
 	unsigned int n_translated;
 	int error;
 
-	unsigned int stack_depth;
+	unsigned int stack_frame_depth;
 	unsigned int adjust_head_location;
 
 	unsigned int map_records_cnt;
+	unsigned int subprog_cnt;
 	struct nfp_bpf_neutral_map **map_records;
+	struct nfp_bpf_subprog_info *subprog;
 
 	struct list_head insns;
 };
@@ -476,6 +521,7 @@ struct nfp_bpf_vnic {
 	unsigned int tgt_done;
 };
 
+bool nfp_is_subprog_start(struct nfp_insn_meta *meta);
 void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt);
 int nfp_bpf_jit(struct nfp_prog *prog);
 bool nfp_bpf_supported_opcode(u8 code);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 6140e4650b71cc249d82f84fefc1fda1efe26b56..ec76f4598039f660c87927297340192535abcc3b 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -208,6 +208,8 @@ static void nfp_prog_free(struct nfp_prog *nfp_prog)
 {
 	struct nfp_insn_meta *meta, *tmp;
 
+	kfree(nfp_prog->subprog);
+
 	list_for_each_entry_safe(meta, tmp, &nfp_prog->insns, l) {
 		list_del(&meta->l);
 		kfree(meta);
@@ -250,18 +252,9 @@ nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn,
 static int nfp_bpf_translate(struct nfp_net *nn, struct bpf_prog *prog)
 {
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
-	unsigned int stack_size;
 	unsigned int max_instr;
 	int err;
 
-	stack_size = nn_readb(nn, NFP_NET_CFG_BPF_STACK_SZ) * 64;
-	if (prog->aux->stack_depth > stack_size) {
-		nn_info(nn, "stack too large: program %dB > FW stack %dB\n",
-			prog->aux->stack_depth, stack_size);
-		return -EOPNOTSUPP;
-	}
-	nfp_prog->stack_depth = round_up(prog->aux->stack_depth, 4);
-
 	max_instr = nn_readw(nn, NFP_NET_CFG_BPF_MAX_LEN);
 	nfp_prog->__prog_alloc_len = max_instr * sizeof(u64);
 
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index db7e186dae56d4c0dda0d3ba59c5408867ef7371..1daa6a0b78321333041ae12b917d3ee0ccd3f88b 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -34,10 +34,12 @@
 #include <linux/bpf.h>
 #include <linux/bpf_verifier.h>
 #include <linux/kernel.h>
+#include <linux/netdevice.h>
 #include <linux/pkt_cls.h>
 
 #include "../nfp_app.h"
 #include "../nfp_main.h"
+#include "../nfp_net.h"
 #include "fw.h"
 #include "main.h"
 
@@ -195,8 +197,9 @@ nfp_bpf_map_call_ok(const char *fname, struct bpf_verifier_env *env,
 }
 
 static int
-nfp_bpf_check_call(struct nfp_prog *nfp_prog, struct bpf_verifier_env *env,
-		   struct nfp_insn_meta *meta)
+nfp_bpf_check_helper_call(struct nfp_prog *nfp_prog,
+			  struct bpf_verifier_env *env,
+			  struct nfp_insn_meta *meta)
 {
 	const struct bpf_reg_state *reg1 = cur_regs(env) + BPF_REG_1;
 	const struct bpf_reg_state *reg2 = cur_regs(env) + BPF_REG_2;
@@ -374,6 +377,9 @@ nfp_bpf_check_stack_access(struct nfp_prog *nfp_prog,
 {
 	s32 old_off, new_off;
 
+	if (reg->frameno != env->cur_state->curframe)
+		meta->flags |= FLAG_INSN_PTR_CALLER_STACK_FRAME;
+
 	if (!tnum_is_const(reg->var_off)) {
 		pr_vlog(env, "variable ptr stack access\n");
 		return -EINVAL;
@@ -668,8 +674,8 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 		return -EINVAL;
 	}
 
-	if (meta->insn.code == (BPF_JMP | BPF_CALL))
-		return nfp_bpf_check_call(nfp_prog, env, meta);
+	if (is_mbpf_helper_call(meta))
+		return nfp_bpf_check_helper_call(nfp_prog, env, meta);
 	if (meta->insn.code == (BPF_JMP | BPF_EXIT))
 		return nfp_bpf_check_exit(nfp_prog, env);
 
@@ -688,6 +694,131 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 	return 0;
 }
 
+static int
+nfp_assign_subprog_idx_and_regs(struct bpf_verifier_env *env,
+				struct nfp_prog *nfp_prog)
+{
+	struct nfp_insn_meta *meta;
+	int index = 0;
+
+	list_for_each_entry(meta, &nfp_prog->insns, l) {
+		if (nfp_is_subprog_start(meta))
+			index++;
+		meta->subprog_idx = index;
+
+		if (meta->insn.dst_reg >= BPF_REG_6 &&
+		    meta->insn.dst_reg <= BPF_REG_9)
+			nfp_prog->subprog[index].needs_reg_push = 1;
+	}
+
+	if (index + 1 != nfp_prog->subprog_cnt) {
+		pr_vlog(env, "BUG: number of processed BPF functions is not consistent (processed %d, expected %d)\n",
+			index + 1, nfp_prog->subprog_cnt);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static unsigned int
+nfp_bpf_get_stack_usage(struct nfp_prog *nfp_prog, unsigned int cnt)
+{
+	struct nfp_insn_meta *meta = nfp_prog_first_meta(nfp_prog);
+	unsigned int max_depth = 0, depth = 0, frame = 0;
+	struct nfp_insn_meta *ret_insn[MAX_CALL_FRAMES];
+	unsigned short frame_depths[MAX_CALL_FRAMES];
+	unsigned short ret_prog[MAX_CALL_FRAMES];
+	unsigned short idx = meta->subprog_idx;
+
+	/* Inspired from check_max_stack_depth() from kernel verifier.
+	 * Starting from main subprogram, walk all instructions and recursively
+	 * walk all callees that given subprogram can call. Since recursion is
+	 * prevented by the kernel verifier, this algorithm only needs a local
+	 * stack of MAX_CALL_FRAMES to remember callsites.
+	 */
+process_subprog:
+	frame_depths[frame] = nfp_prog->subprog[idx].stack_depth;
+	frame_depths[frame] = round_up(frame_depths[frame], STACK_FRAME_ALIGN);
+	depth += frame_depths[frame];
+	max_depth = max(max_depth, depth);
+
+continue_subprog:
+	for (; meta != nfp_prog_last_meta(nfp_prog) && meta->subprog_idx == idx;
+	     meta = nfp_meta_next(meta)) {
+		if (!is_mbpf_pseudo_call(meta))
+			continue;
+
+		/* We found a call to a subprogram. Remember instruction to
+		 * return to and subprog id.
+		 */
+		ret_insn[frame] = nfp_meta_next(meta);
+		ret_prog[frame] = idx;
+
+		/* Find the callee and start processing it. */
+		meta = nfp_bpf_goto_meta(nfp_prog, meta,
+					 meta->n + 1 + meta->insn.imm, cnt);
+		idx = meta->subprog_idx;
+		frame++;
+		goto process_subprog;
+	}
+	/* End of for() loop means the last instruction of the subprog was
+	 * reached. If we popped all stack frames, return; otherwise, go on
+	 * processing remaining instructions from the caller.
+	 */
+	if (frame == 0)
+		return max_depth;
+
+	depth -= frame_depths[frame];
+	frame--;
+	meta = ret_insn[frame];
+	idx = ret_prog[frame];
+	goto continue_subprog;
+}
+
+static int nfp_bpf_finalize(struct bpf_verifier_env *env)
+{
+	unsigned int stack_size, stack_needed;
+	struct bpf_subprog_info *info;
+	struct nfp_prog *nfp_prog;
+	struct nfp_net *nn;
+	int i;
+
+	nfp_prog = env->prog->aux->offload->dev_priv;
+	nfp_prog->subprog_cnt = env->subprog_cnt;
+	nfp_prog->subprog = kcalloc(nfp_prog->subprog_cnt,
+				    sizeof(nfp_prog->subprog[0]), GFP_KERNEL);
+	if (!nfp_prog->subprog)
+		return -ENOMEM;
+
+	nfp_assign_subprog_idx_and_regs(env, nfp_prog);
+
+	info = env->subprog_info;
+	for (i = 0; i < nfp_prog->subprog_cnt; i++) {
+		nfp_prog->subprog[i].stack_depth = info[i].stack_depth;
+
+		if (i == 0)
+			continue;
+
+		/* Account for size of return address. */
+		nfp_prog->subprog[i].stack_depth += REG_WIDTH;
+		/* Account for size of saved registers, if necessary. */
+		if (nfp_prog->subprog[i].needs_reg_push)
+			nfp_prog->subprog[i].stack_depth += BPF_REG_SIZE * 4;
+	}
+
+	nn = netdev_priv(env->prog->aux->offload->netdev);
+	stack_size = nn_readb(nn, NFP_NET_CFG_BPF_STACK_SZ) * 64;
+	stack_needed = nfp_bpf_get_stack_usage(nfp_prog, env->prog->len);
+	if (stack_needed > stack_size) {
+		pr_vlog(env, "stack too large: program %dB > FW stack %dB\n",
+			stack_needed, stack_size);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops = {
-	.insn_hook = nfp_verify_insn,
+	.insn_hook	= nfp_verify_insn,
+	.finalize	= nfp_bpf_finalize,
 };
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
index fad0e62a910ccb6e7f461e04f1936f625f38932d..5b257c603e911be9cf158931ee481c6a1cbe1842 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
@@ -82,6 +82,15 @@
 #define OP_BR_BIT_ADDR_LO	OP_BR_ADDR_LO
 #define OP_BR_BIT_ADDR_HI	OP_BR_ADDR_HI
 
+#define OP_BR_ALU_BASE		0x0e800000000ULL
+#define OP_BR_ALU_BASE_MASK	0x0ff80000000ULL
+#define OP_BR_ALU_A_SRC		0x000000003ffULL
+#define OP_BR_ALU_B_SRC		0x000000ffc00ULL
+#define OP_BR_ALU_DEFBR		0x00000300000ULL
+#define OP_BR_ALU_IMM_HI	0x0007fc00000ULL
+#define OP_BR_ALU_SRC_LMEXTN	0x40000000000ULL
+#define OP_BR_ALU_DST_LMEXTN	0x80000000000ULL
+
 static inline bool nfp_is_br(u64 insn)
 {
 	return (insn & OP_BR_BASE_MASK) == OP_BR_BASE ||
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 12f100392ed1159d53fd7ed308465e9f33191708..eb6c1debb3cbc239a81895be3178af2f8a775ad7 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -86,8 +86,14 @@ nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn)
 	return 0;
 }
 
+static int nsim_bpf_finalize(struct bpf_verifier_env *env)
+{
+	return 0;
+}
+
 static const struct bpf_prog_offload_ops nsim_bpf_analyzer_ops = {
-	.insn_hook = nsim_bpf_verify_insn,
+	.insn_hook	= nsim_bpf_verify_insn,
+	.finalize	= nsim_bpf_finalize,
 };
 
 static bool nsim_xdp_offload_active(struct netdevsim *ns)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ac36683276a09d21ce458fe763fe6bc6055b91ea..9fb8d9c5cea46f4a7c66448cd57c1ef34f361041 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -269,6 +269,7 @@ struct bpf_verifier_ops {
 struct bpf_prog_offload_ops {
 	int (*insn_hook)(struct bpf_verifier_env *env,
 			 int insn_idx, int prev_insn_idx);
+	int (*finalize)(struct bpf_verifier_env *env);
 };
 
 struct bpf_prog_offload {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index e9a11143dd5e8d9df8cb2fb4a49b133e2a44d3e6..5dbb9e5de7471a4253dbb83843e44946e00c686d 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -264,5 +264,6 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env)
 int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env);
 int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
 				 int insn_idx, int prev_insn_idx);
+int bpf_prog_offload_finalize(struct bpf_verifier_env *env);
 
 #endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 3c7aedc0c3e8c8f68ba50773b0fdd4ede925b442..ed670cd45cfe40ed7277468b8a6661b22eac9ec9 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -172,6 +172,24 @@ int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
 	return ret;
 }
 
+int bpf_prog_offload_finalize(struct bpf_verifier_env *env)
+{
+	struct bpf_prog_offload *offload;
+	int ret = -ENODEV;
+
+	down_read(&bpf_devs_lock);
+	offload = env->prog->aux->offload;
+	if (offload) {
+		if (offload->dev_ops->finalize)
+			ret = offload->dev_ops->finalize(env);
+		else
+			ret = 0;
+	}
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
 static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
 {
 	struct bpf_prog_offload *offload = prog->aux->offload;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 012fe5e8841343090f5eda892ce4055bf5fa2e43..b0a1e040edb481891ba41979777d6c46c910e58e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1011,10 +1011,6 @@ static int check_subprogs(struct bpf_verifier_env *env)
 			verbose(env, "function calls to other bpf functions are allowed for root only\n");
 			return -EPERM;
 		}
-		if (bpf_prog_is_dev_bound(env->prog->aux)) {
-			verbose(env, "function calls in offloaded programs are not supported yet\n");
-			return -EINVAL;
-		}
 		ret = add_subprog(env, i + insn[i].imm + 1);
 		if (ret < 0)
 			return ret;
@@ -6569,10 +6565,10 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 	struct bpf_insn *insn = prog->insnsi;
 	int i, depth;
 #endif
-	int err;
+	int err = 0;
 
-	err = 0;
-	if (env->prog->jit_requested) {
+	if (env->prog->jit_requested &&
+	    !bpf_prog_is_dev_bound(env->prog->aux)) {
 		err = jit_subprogs(env);
 		if (err == 0)
 			return 0;
@@ -6964,6 +6960,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 		env->cur_state = NULL;
 	}
 
+	if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux))
+		ret = bpf_prog_offload_finalize(env);
+
 skip_full_check:
 	while (!pop_stack(env, NULL, NULL));
 	free_states(env);
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 63b47b8e5e419e2363d698042225bc7f63d66859..d61eaeb54a8edf50afea1e194b894d649e6b73ad 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -68,7 +68,9 @@ static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	snprintf(netinfo->devices[netinfo->used_len].devname,
 		 sizeof(netinfo->devices[netinfo->used_len].devname),
 		 "%s",
-		 tb[IFLA_IFNAME] ? nla_getattr_str(tb[IFLA_IFNAME]) : "");
+		 tb[IFLA_IFNAME]
+			 ? libbpf_nla_getattr_str(tb[IFLA_IFNAME])
+			 : "");
 	netinfo->used_len++;
 
 	return do_xdp_dump(ifinfo, tb);
@@ -82,7 +84,7 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	if (tcinfo->is_qdisc) {
 		/* skip clsact qdisc */
 		if (tb[TCA_KIND] &&
-		    strcmp(nla_data(tb[TCA_KIND]), "clsact") == 0)
+		    strcmp(libbpf_nla_data(tb[TCA_KIND]), "clsact") == 0)
 			return 0;
 		if (info->tcm_handle == 0)
 			return 0;
@@ -100,7 +102,9 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	snprintf(tcinfo->handle_array[tcinfo->used_len].kind,
 		 sizeof(tcinfo->handle_array[tcinfo->used_len].kind),
 		 "%s",
-		 tb[TCA_KIND] ? nla_getattr_str(tb[TCA_KIND]) : "unknown");
+		 tb[TCA_KIND]
+			 ? libbpf_nla_getattr_str(tb[TCA_KIND])
+			 : "unknown");
 	tcinfo->used_len++;
 
 	return 0;
@@ -126,14 +130,14 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
 	tcinfo.array_len = 0;
 
 	tcinfo.is_qdisc = false;
-	ret = nl_get_class(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
-			   &tcinfo);
+	ret = libbpf_nl_get_class(sock, nl_pid, dev->ifindex,
+				  dump_class_qdisc_nlmsg, &tcinfo);
 	if (ret)
 		goto out;
 
 	tcinfo.is_qdisc = true;
-	ret = nl_get_qdisc(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
-			   &tcinfo);
+	ret = libbpf_nl_get_qdisc(sock, nl_pid, dev->ifindex,
+				  dump_class_qdisc_nlmsg, &tcinfo);
 	if (ret)
 		goto out;
 
@@ -141,10 +145,9 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
 	filter_info.ifindex = dev->ifindex;
 	for (i = 0; i < tcinfo.used_len; i++) {
 		filter_info.kind = tcinfo.handle_array[i].kind;
-		ret = nl_get_filter(sock, nl_pid, dev->ifindex,
-				    tcinfo.handle_array[i].handle,
-				    dump_filter_nlmsg,
-				    &filter_info);
+		ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex,
+					   tcinfo.handle_array[i].handle,
+					   dump_filter_nlmsg, &filter_info);
 		if (ret)
 			goto out;
 	}
@@ -152,22 +155,22 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
 	/* root, ingress and egress handle */
 	handle = TC_H_ROOT;
 	filter_info.kind = "root";
-	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
-			    dump_filter_nlmsg, &filter_info);
+	ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+				   dump_filter_nlmsg, &filter_info);
 	if (ret)
 		goto out;
 
 	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS);
 	filter_info.kind = "clsact/ingress";
-	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
-			    dump_filter_nlmsg, &filter_info);
+	ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+				   dump_filter_nlmsg, &filter_info);
 	if (ret)
 		goto out;
 
 	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS);
 	filter_info.kind = "clsact/egress";
-	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
-			    dump_filter_nlmsg, &filter_info);
+	ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+				   dump_filter_nlmsg, &filter_info);
 	if (ret)
 		goto out;
 
@@ -195,7 +198,7 @@ static int do_show(int argc, char **argv)
 		usage();
 	}
 
-	sock = bpf_netlink_open(&nl_pid);
+	sock = libbpf_netlink_open(&nl_pid);
 	if (sock < 0) {
 		fprintf(stderr, "failed to open netlink sock\n");
 		return -1;
@@ -210,7 +213,7 @@ static int do_show(int argc, char **argv)
 		jsonw_start_array(json_wtr);
 	NET_START_OBJECT;
 	NET_START_ARRAY("xdp", "%s:\n");
-	ret = nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array);
+	ret = libbpf_nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array);
 	NET_END_ARRAY("\n");
 
 	if (!ret) {
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
index 6f5e9cc6836c385651daf02a112f18a578384f7a..4e9f4531269fabe66b5d0ef98c45eb2f52a6398b 100644
--- a/tools/bpf/bpftool/netlink_dumper.c
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -21,7 +21,7 @@ static void xdp_dump_prog_id(struct nlattr **tb, int attr,
 	if (new_json_object)
 		NET_START_OBJECT
 	NET_DUMP_STR("mode", " %s", mode);
-	NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[attr]))
+	NET_DUMP_UINT("id", " id %u", libbpf_nla_getattr_u32(tb[attr]))
 	if (new_json_object)
 		NET_END_OBJECT
 }
@@ -32,13 +32,13 @@ static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex,
 	struct nlattr *tb[IFLA_XDP_MAX + 1];
 	unsigned char mode;
 
-	if (nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0)
 		return -1;
 
 	if (!tb[IFLA_XDP_ATTACHED])
 		return 0;
 
-	mode = nla_getattr_u8(tb[IFLA_XDP_ATTACHED]);
+	mode = libbpf_nla_getattr_u8(tb[IFLA_XDP_ATTACHED]);
 	if (mode == XDP_ATTACHED_NONE)
 		return 0;
 
@@ -75,14 +75,14 @@ int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb)
 		return 0;
 
 	return do_xdp_dump_one(tb[IFLA_XDP], ifinfo->ifi_index,
-			       nla_getattr_str(tb[IFLA_IFNAME]));
+			       libbpf_nla_getattr_str(tb[IFLA_IFNAME]));
 }
 
 static int do_bpf_dump_one_act(struct nlattr *attr)
 {
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
 
-	if (nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	if (!tb[TCA_ACT_BPF_PARMS])
@@ -91,10 +91,10 @@ static int do_bpf_dump_one_act(struct nlattr *attr)
 	NET_START_OBJECT_NESTED2;
 	if (tb[TCA_ACT_BPF_NAME])
 		NET_DUMP_STR("name", "%s",
-			     nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
+			     libbpf_nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
 	if (tb[TCA_ACT_BPF_ID])
 		NET_DUMP_UINT("id", " id %u",
-			      nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
+			      libbpf_nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
 	NET_END_OBJECT_NESTED;
 	return 0;
 }
@@ -106,10 +106,11 @@ static int do_dump_one_act(struct nlattr *attr)
 	if (!attr)
 		return 0;
 
-	if (nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
-	if (tb[TCA_ACT_KIND] && strcmp(nla_data(tb[TCA_ACT_KIND]), "bpf") == 0)
+	if (tb[TCA_ACT_KIND] &&
+	    strcmp(libbpf_nla_data(tb[TCA_ACT_KIND]), "bpf") == 0)
 		return do_bpf_dump_one_act(tb[TCA_ACT_OPTIONS]);
 
 	return 0;
@@ -120,7 +121,7 @@ static int do_bpf_act_dump(struct nlattr *attr)
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
 	int act, ret;
 
-	if (nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	NET_START_ARRAY("act", " %s [");
@@ -139,13 +140,15 @@ static int do_bpf_filter_dump(struct nlattr *attr)
 	struct nlattr *tb[TCA_BPF_MAX + 1];
 	int ret;
 
-	if (nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	if (tb[TCA_BPF_NAME])
-		NET_DUMP_STR("name", " %s", nla_getattr_str(tb[TCA_BPF_NAME]));
+		NET_DUMP_STR("name", " %s",
+			     libbpf_nla_getattr_str(tb[TCA_BPF_NAME]));
 	if (tb[TCA_BPF_ID])
-		NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[TCA_BPF_ID]));
+		NET_DUMP_UINT("id", " id %u",
+			      libbpf_nla_getattr_u32(tb[TCA_BPF_ID]));
 	if (tb[TCA_BPF_ACT]) {
 		ret = do_bpf_act_dump(tb[TCA_BPF_ACT]);
 		if (ret)
@@ -160,7 +163,8 @@ int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind,
 {
 	int ret = 0;
 
-	if (tb[TCA_OPTIONS] && strcmp(nla_data(tb[TCA_KIND]), "bpf") == 0) {
+	if (tb[TCA_OPTIONS] &&
+	    strcmp(libbpf_nla_data(tb[TCA_KIND]), "bpf") == 0) {
 		NET_START_OBJECT;
 		if (devname[0] != '\0')
 			NET_DUMP_STR("devname", "%s", devname);
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 3624557550a1fae3c349a4904f7298adc170245d..f48e18805902f222b4b9509fbf77f60be8072ed8 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 # Most of this file is copied from tools/lib/traceevent/Makefile
 
 BPF_VERSION = 0
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index eba3ad604244d89600b4ac1ecee1c7a0932b9dc3..f1ba022fd659e30a507daf0c603fbd3900f01d8d 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 /*
  * common eBPF ELF operations.
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index c3145ab3bdcaca155aef554750cded18018b8e28..f57a2a09761df2022d4ce24ba996b53ee073bb1b 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 
 /*
  * common eBPF ELF operations.
@@ -20,8 +20,8 @@
  * You should have received a copy of the GNU Lesser General Public
  * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
-#ifndef __BPF_BPF_H
-#define __BPF_BPF_H
+#ifndef __LIBBPF_BPF_H
+#define __LIBBPF_BPF_H
 
 #include <linux/bpf.h>
 #include <stdbool.h>
@@ -112,4 +112,4 @@ int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
 int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
 		      __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset,
 		      __u64 *probe_addr);
-#endif
+#endif /* __LIBBPF_BPF_H */
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index cf94b0770522ffb57246fec6f3f4dd7eb9598ec2..449591aa99000dd35968371ca0656013a6c52cc4 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
 #include <stdlib.h>
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 4897e0724d4ec6180e1262338ef6bd0e9fd72ab9..6db5462bb2ef9e0b8adab5fa984b6a434e40aea0 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -1,8 +1,8 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 /* Copyright (c) 2018 Facebook */
 
-#ifndef __BPF_BTF_H
-#define __BPF_BTF_H
+#ifndef __LIBBPF_BTF_H
+#define __LIBBPF_BTF_H
 
 #include <linux/types.h>
 
@@ -23,4 +23,4 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id);
 int btf__fd(const struct btf *btf);
 const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 
-#endif
+#endif /* __LIBBPF_BTF_H */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a1e015bfce67e8035b939ea3ffa5b0eb73402769..927f4321f8ad6d86b94f36ae91cf4c672b609548 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 /*
  * Common eBPF ELF object loading operations.
@@ -7,19 +7,6 @@
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
  * Copyright (C) 2017 Nicira, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 
 #ifndef _GNU_SOURCE
@@ -472,7 +459,8 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 		obj->efile.fd = open(obj->path, O_RDONLY);
 		if (obj->efile.fd < 0) {
 			char errmsg[STRERR_BUFSIZE];
-			char *cp = str_error(errno, errmsg, sizeof(errmsg));
+			char *cp = libbpf_strerror_r(errno, errmsg,
+						     sizeof(errmsg));
 
 			pr_warning("failed to open %s: %s\n", obj->path, cp);
 			return -errno;
@@ -813,7 +801,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 						      data->d_size, name, idx);
 			if (err) {
 				char errmsg[STRERR_BUFSIZE];
-				char *cp = str_error(-err, errmsg, sizeof(errmsg));
+				char *cp = libbpf_strerror_r(-err, errmsg,
+							     sizeof(errmsg));
 
 				pr_warning("failed to alloc program %s (%s): %s",
 					   name, obj->path, cp);
@@ -1142,7 +1131,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 
 		*pfd = bpf_create_map_xattr(&create_attr);
 		if (*pfd < 0 && create_attr.btf_key_type_id) {
-			cp = str_error(errno, errmsg, sizeof(errmsg));
+			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 			pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
 				   map->name, cp, errno);
 			create_attr.btf_fd = 0;
@@ -1157,7 +1146,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 			size_t j;
 
 			err = *pfd;
-			cp = str_error(errno, errmsg, sizeof(errmsg));
+			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 			pr_warning("failed to create map (name: '%s'): %s\n",
 				   map->name, cp);
 			for (j = 0; j < i; j++)
@@ -1341,7 +1330,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 	}
 
 	ret = -LIBBPF_ERRNO__LOAD;
-	cp = str_error(errno, errmsg, sizeof(errmsg));
+	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 	pr_warning("load bpf program failed: %s\n", cp);
 
 	if (log_buf && log_buf[0] != '\0') {
@@ -1379,7 +1368,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 
 int
 bpf_program__load(struct bpf_program *prog,
-		  char *license, u32 kern_version)
+		  char *license, __u32 kern_version)
 {
 	int err = 0, fd, i;
 
@@ -1657,7 +1646,7 @@ static int check_path(const char *path)
 
 	dir = dirname(dname);
 	if (statfs(dir, &st_fs)) {
-		cp = str_error(errno, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 		pr_warning("failed to statfs %s: %s\n", dir, cp);
 		err = -errno;
 	}
@@ -1693,7 +1682,7 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 	}
 
 	if (bpf_obj_pin(prog->instances.fds[instance], path)) {
-		cp = str_error(errno, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 		pr_warning("failed to pin program: %s\n", cp);
 		return -errno;
 	}
@@ -1711,7 +1700,7 @@ static int make_dir(const char *path)
 		err = -errno;
 
 	if (err) {
-		cp = str_error(-err, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
 		pr_warning("failed to mkdir %s: %s\n", path, cp);
 	}
 	return err;
@@ -1773,7 +1762,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 	}
 
 	if (bpf_obj_pin(map->fd, path)) {
-		cp = str_error(errno, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 		pr_warning("failed to pin map: %s\n", cp);
 		return -errno;
 	}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 2ed24d3f80b36adba93ab968ff7727142ba80131..8af8d36639910bd625cd17eb4c29a8084e60cf8f 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 
 /*
  * Common eBPF ELF object loading operations.
@@ -6,22 +6,9 @@
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
-#ifndef __BPF_LIBBPF_H
-#define __BPF_LIBBPF_H
+#ifndef __LIBBPF_LIBBPF_H
+#define __LIBBPF_LIBBPF_H
 
 #include <stdio.h>
 #include <stdint.h>
@@ -129,7 +116,7 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex);
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
 int bpf_program__load(struct bpf_program *prog, char *license,
-		      u32 kern_version);
+		      __u32 kern_version);
 int bpf_program__fd(struct bpf_program *prog);
 int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 			      int instance);
@@ -304,18 +291,15 @@ int bpf_perf_event_read_simple(void *mem, unsigned long size,
 			       void **buf, size_t *buf_len,
 			       bpf_perf_event_print_t fn, void *priv);
 
-struct nlmsghdr;
 struct nlattr;
-typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
-typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t,
-			      void *cookie);
-int bpf_netlink_open(unsigned int *nl_pid);
-int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
-		void *cookie);
-int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_class_nlmsg, void *cookie);
-int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
-int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
-		  dump_nlmsg_t dump_filter_nlmsg, void *cookie);
-#endif
+typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
+int libbpf_netlink_open(unsigned int *nl_pid);
+int libbpf_nl_get_link(int sock, unsigned int nl_pid,
+		       libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie);
+int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie);
+int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
+int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie);
+#endif /* __LIBBPF_LIBBPF_H */
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index 451283328fa907d5cc1d2e415846cdc2a37f241a..cf11f30606e15d6b152facdee95dff500c97bff2 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -5,19 +5,6 @@
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
  * Copyright (C) 2017 Nicira, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 
 #undef _GNU_SOURCE
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index fde1d7bf8199ede8fbd0d54e0f2bcd04f5af95fc..0ce67aea8f3becd560fd4a11b6e51ddd9dac1563 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
 #include <stdlib.h>
@@ -18,7 +18,10 @@
 #define SOL_NETLINK 270
 #endif
 
-int bpf_netlink_open(__u32 *nl_pid)
+typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t,
+			      void *cookie);
+
+int libbpf_netlink_open(__u32 *nl_pid)
 {
 	struct sockaddr_nl sa;
 	socklen_t addrlen;
@@ -62,7 +65,7 @@ int bpf_netlink_open(__u32 *nl_pid)
 }
 
 static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
-			    __dump_nlmsg_t _fn, dump_nlmsg_t fn,
+			    __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
 			    void *cookie)
 {
 	bool multipart = true;
@@ -100,7 +103,7 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 				if (!err->error)
 					continue;
 				ret = err->error;
-				nla_dump_errormsg(nh);
+				libbpf_nla_dump_errormsg(nh);
 				goto done;
 			case NLMSG_DONE:
 				return 0;
@@ -130,7 +133,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	} req;
 	__u32 nl_pid;
 
-	sock = bpf_netlink_open(&nl_pid);
+	sock = libbpf_netlink_open(&nl_pid);
 	if (sock < 0)
 		return sock;
 
@@ -178,8 +181,8 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	return ret;
 }
 
-static int __dump_link_nlmsg(struct nlmsghdr *nlh, dump_nlmsg_t dump_link_nlmsg,
-			     void *cookie)
+static int __dump_link_nlmsg(struct nlmsghdr *nlh,
+			     libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {
 	struct nlattr *tb[IFLA_MAX + 1], *attr;
 	struct ifinfomsg *ifi = NLMSG_DATA(nlh);
@@ -187,14 +190,14 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh, dump_nlmsg_t dump_link_nlmsg,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
 	attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi)));
-	if (nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_link_nlmsg(cookie, ifi, tb);
 }
 
-int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
-		void *cookie)
+int libbpf_nl_get_link(int sock, unsigned int nl_pid,
+		       libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
@@ -216,7 +219,8 @@ int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
 }
 
 static int __dump_class_nlmsg(struct nlmsghdr *nlh,
-			      dump_nlmsg_t dump_class_nlmsg, void *cookie)
+			      libbpf_dump_nlmsg_t dump_class_nlmsg,
+			      void *cookie)
 {
 	struct nlattr *tb[TCA_MAX + 1], *attr;
 	struct tcmsg *t = NLMSG_DATA(nlh);
@@ -224,14 +228,14 @@ static int __dump_class_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
 	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_class_nlmsg(cookie, t, tb);
 }
 
-int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_class_nlmsg, void *cookie)
+int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
@@ -254,7 +258,8 @@ int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
 }
 
 static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
-			      dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+			      libbpf_dump_nlmsg_t dump_qdisc_nlmsg,
+			      void *cookie)
 {
 	struct nlattr *tb[TCA_MAX + 1], *attr;
 	struct tcmsg *t = NLMSG_DATA(nlh);
@@ -262,14 +267,14 @@ static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
 	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_qdisc_nlmsg(cookie, t, tb);
 }
 
-int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
@@ -292,7 +297,8 @@ int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
 }
 
 static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
-			       dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+			       libbpf_dump_nlmsg_t dump_filter_nlmsg,
+			       void *cookie)
 {
 	struct nlattr *tb[TCA_MAX + 1], *attr;
 	struct tcmsg *t = NLMSG_DATA(nlh);
@@ -300,14 +306,14 @@ static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
 	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_filter_nlmsg(cookie, t, tb);
 }
 
-int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
-		  dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 49f514119bdb083e24b5720f9d077aaa63b053d9..1e69c0c8d413f7fb54830783c19c4dac4875fa8f 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -1,13 +1,8 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 /*
  * NETLINK      Netlink attributes
  *
- *	This library is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU Lesser General Public
- *	License as published by the Free Software Foundation version 2.1
- *	of the License.
- *
  * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
  */
 
@@ -17,13 +12,13 @@
 #include <string.h>
 #include <stdio.h>
 
-static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = {
-	[NLA_U8]	= sizeof(uint8_t),
-	[NLA_U16]	= sizeof(uint16_t),
-	[NLA_U32]	= sizeof(uint32_t),
-	[NLA_U64]	= sizeof(uint64_t),
-	[NLA_STRING]	= 1,
-	[NLA_FLAG]	= 0,
+static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = {
+	[LIBBPF_NLA_U8]		= sizeof(uint8_t),
+	[LIBBPF_NLA_U16]	= sizeof(uint16_t),
+	[LIBBPF_NLA_U32]	= sizeof(uint32_t),
+	[LIBBPF_NLA_U64]	= sizeof(uint64_t),
+	[LIBBPF_NLA_STRING]	= 1,
+	[LIBBPF_NLA_FLAG]	= 0,
 };
 
 static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
@@ -47,9 +42,9 @@ static int nla_type(const struct nlattr *nla)
 }
 
 static int validate_nla(struct nlattr *nla, int maxtype,
-			struct nla_policy *policy)
+			struct libbpf_nla_policy *policy)
 {
-	struct nla_policy *pt;
+	struct libbpf_nla_policy *pt;
 	unsigned int minlen = 0;
 	int type = nla_type(nla);
 
@@ -58,23 +53,24 @@ static int validate_nla(struct nlattr *nla, int maxtype,
 
 	pt = &policy[type];
 
-	if (pt->type > NLA_TYPE_MAX)
+	if (pt->type > LIBBPF_NLA_TYPE_MAX)
 		return 0;
 
 	if (pt->minlen)
 		minlen = pt->minlen;
-	else if (pt->type != NLA_UNSPEC)
+	else if (pt->type != LIBBPF_NLA_UNSPEC)
 		minlen = nla_attr_minlen[pt->type];
 
-	if (nla_len(nla) < minlen)
+	if (libbpf_nla_len(nla) < minlen)
 		return -1;
 
-	if (pt->maxlen && nla_len(nla) > pt->maxlen)
+	if (pt->maxlen && libbpf_nla_len(nla) > pt->maxlen)
 		return -1;
 
-	if (pt->type == NLA_STRING) {
-		char *data = nla_data(nla);
-		if (data[nla_len(nla) - 1] != '\0')
+	if (pt->type == LIBBPF_NLA_STRING) {
+		char *data = libbpf_nla_data(nla);
+
+		if (data[libbpf_nla_len(nla) - 1] != '\0')
 			return -1;
 	}
 
@@ -104,15 +100,15 @@ static inline int nlmsg_len(const struct nlmsghdr *nlh)
  * @see nla_validate
  * @return 0 on success or a negative error code.
  */
-int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
-	      struct nla_policy *policy)
+int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
+		     int len, struct libbpf_nla_policy *policy)
 {
 	struct nlattr *nla;
 	int rem, err;
 
 	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
 
-	nla_for_each_attr(nla, head, len, rem) {
+	libbpf_nla_for_each_attr(nla, head, len, rem) {
 		int type = nla_type(nla);
 
 		if (type > maxtype)
@@ -144,23 +140,25 @@ int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
  * @arg policy          Attribute validation policy.
  *
  * Feeds the stream of attributes nested into the specified attribute
- * to nla_parse().
+ * to libbpf_nla_parse().
  *
- * @see nla_parse
+ * @see libbpf_nla_parse
  * @return 0 on success or a negative error code.
  */
-int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
-		     struct nla_policy *policy)
+int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
+			    struct nlattr *nla,
+			    struct libbpf_nla_policy *policy)
 {
-	return nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy);
+	return libbpf_nla_parse(tb, maxtype, libbpf_nla_data(nla),
+				libbpf_nla_len(nla), policy);
 }
 
 /* dump netlink extended ack error message */
-int nla_dump_errormsg(struct nlmsghdr *nlh)
+int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh)
 {
-	struct nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {
-		[NLMSGERR_ATTR_MSG]	= { .type = NLA_STRING },
-		[NLMSGERR_ATTR_OFFS]	= { .type = NLA_U32 },
+	struct libbpf_nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {
+		[NLMSGERR_ATTR_MSG]	= { .type = LIBBPF_NLA_STRING },
+		[NLMSGERR_ATTR_OFFS]	= { .type = LIBBPF_NLA_U32 },
 	};
 	struct nlattr *tb[NLMSGERR_ATTR_MAX + 1], *attr;
 	struct nlmsgerr *err;
@@ -181,14 +179,15 @@ int nla_dump_errormsg(struct nlmsghdr *nlh)
 	attr = (struct nlattr *) ((void *) err + hlen);
 	alen = nlh->nlmsg_len - hlen;
 
-	if (nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) {
+	if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen,
+			     extack_policy) != 0) {
 		fprintf(stderr,
 			"Failed to parse extended error attributes\n");
 		return 0;
 	}
 
 	if (tb[NLMSGERR_ATTR_MSG])
-		errmsg = (char *) nla_data(tb[NLMSGERR_ATTR_MSG]);
+		errmsg = (char *) libbpf_nla_data(tb[NLMSGERR_ATTR_MSG]);
 
 	fprintf(stderr, "Kernel error message: %s\n", errmsg);
 
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index a6e2396bce7ccba09f3d262741eaf7f8c81fc94c..6cc3ac91690f5e212b1cc2018d0a1c994c0e6fdf 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -1,18 +1,13 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 
 /*
  * NETLINK      Netlink attributes
  *
- *	This library is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU Lesser General Public
- *	License as published by the Free Software Foundation version 2.1
- *	of the License.
- *
  * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
  */
 
-#ifndef __NLATTR_H
-#define __NLATTR_H
+#ifndef __LIBBPF_NLATTR_H
+#define __LIBBPF_NLATTR_H
 
 #include <stdint.h>
 #include <linux/netlink.h>
@@ -23,19 +18,19 @@
  * Standard attribute types to specify validation policy
  */
 enum {
-	NLA_UNSPEC,	/**< Unspecified type, binary data chunk */
-	NLA_U8,		/**< 8 bit integer */
-	NLA_U16,	/**< 16 bit integer */
-	NLA_U32,	/**< 32 bit integer */
-	NLA_U64,	/**< 64 bit integer */
-	NLA_STRING,	/**< NUL terminated character string */
-	NLA_FLAG,	/**< Flag */
-	NLA_MSECS,	/**< Micro seconds (64bit) */
-	NLA_NESTED,	/**< Nested attributes */
-	__NLA_TYPE_MAX,
+	LIBBPF_NLA_UNSPEC,	/**< Unspecified type, binary data chunk */
+	LIBBPF_NLA_U8,		/**< 8 bit integer */
+	LIBBPF_NLA_U16,		/**< 16 bit integer */
+	LIBBPF_NLA_U32,		/**< 32 bit integer */
+	LIBBPF_NLA_U64,		/**< 64 bit integer */
+	LIBBPF_NLA_STRING,	/**< NUL terminated character string */
+	LIBBPF_NLA_FLAG,	/**< Flag */
+	LIBBPF_NLA_MSECS,	/**< Micro seconds (64bit) */
+	LIBBPF_NLA_NESTED,	/**< Nested attributes */
+	__LIBBPF_NLA_TYPE_MAX,
 };
 
-#define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1)
+#define LIBBPF_NLA_TYPE_MAX (__LIBBPF_NLA_TYPE_MAX - 1)
 
 /**
  * @ingroup attr
@@ -43,8 +38,8 @@ enum {
  *
  * See section @core_doc{core_attr_parse,Attribute Parsing} for more details.
  */
-struct nla_policy {
-	/** Type of attribute or NLA_UNSPEC */
+struct libbpf_nla_policy {
+	/** Type of attribute or LIBBPF_NLA_UNSPEC */
 	uint16_t	type;
 
 	/** Minimal length of payload required */
@@ -62,49 +57,50 @@ struct nla_policy {
  * @arg len	length of attribute stream
  * @arg rem	initialized to len, holds bytes currently remaining in stream
  */
-#define nla_for_each_attr(pos, head, len, rem) \
+#define libbpf_nla_for_each_attr(pos, head, len, rem) \
 	for (pos = head, rem = len; \
 	     nla_ok(pos, rem); \
 	     pos = nla_next(pos, &(rem)))
 
 /**
- * nla_data - head of payload
+ * libbpf_nla_data - head of payload
  * @nla: netlink attribute
  */
-static inline void *nla_data(const struct nlattr *nla)
+static inline void *libbpf_nla_data(const struct nlattr *nla)
 {
 	return (char *) nla + NLA_HDRLEN;
 }
 
-static inline uint8_t nla_getattr_u8(const struct nlattr *nla)
+static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla)
 {
-	return *(uint8_t *)nla_data(nla);
+	return *(uint8_t *)libbpf_nla_data(nla);
 }
 
-static inline uint32_t nla_getattr_u32(const struct nlattr *nla)
+static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla)
 {
-	return *(uint32_t *)nla_data(nla);
+	return *(uint32_t *)libbpf_nla_data(nla);
 }
 
-static inline const char *nla_getattr_str(const struct nlattr *nla)
+static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla)
 {
-	return (const char *)nla_data(nla);
+	return (const char *)libbpf_nla_data(nla);
 }
 
 /**
- * nla_len - length of payload
+ * libbpf_nla_len - length of payload
  * @nla: netlink attribute
  */
-static inline int nla_len(const struct nlattr *nla)
+static inline int libbpf_nla_len(const struct nlattr *nla)
 {
 	return nla->nla_len - NLA_HDRLEN;
 }
 
-int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
-	      struct nla_policy *policy);
-int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
-		     struct nla_policy *policy);
+int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
+		     int len, struct libbpf_nla_policy *policy);
+int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
+			    struct nlattr *nla,
+			    struct libbpf_nla_policy *policy);
 
-int nla_dump_errormsg(struct nlmsghdr *nlh);
+int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh);
 
-#endif /* __NLATTR_H */
+#endif /* __LIBBPF_NLATTR_H */
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
index b8798114a3578c90d74f66689c1c49f49ffcc333..00e48ac5b806a2a58acacba02f092af42b425d13 100644
--- a/tools/lib/bpf/str_error.c
+++ b/tools/lib/bpf/str_error.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 #undef _GNU_SOURCE
 #include <string.h>
 #include <stdio.h>
@@ -9,7 +9,7 @@
  * libc, while checking strerror_r() return to avoid having to check this in
  * all places calling it.
  */
-char *str_error(int err, char *dst, int len)
+char *libbpf_strerror_r(int err, char *dst, int len)
 {
 	int ret = strerror_r(err, dst, len);
 	if (ret)
diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h
index 355b1db571d118432f11eaa9fe22386aa83a6456..a139334d57b603db5e2b4475740ecac5bdc4d36f 100644
--- a/tools/lib/bpf/str_error.h
+++ b/tools/lib/bpf/str_error.h
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: LGPL-2.1
-#ifndef BPF_STR_ERROR
-#define BPF_STR_ERROR
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __LIBBPF_STR_ERROR_H
+#define __LIBBPF_STR_ERROR_H
 
-char *str_error(int err, char *dst, int len);
-#endif // BPF_STR_ERROR
+char *libbpf_strerror_r(int err, char *dst, int len);
+#endif /* __LIBBPF_STR_ERROR_H */