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

Daniel Borkmann says:

====================
bpf-next 2022-02-17

We've added 29 non-merge commits during the last 8 day(s) which contain
a total of 34 files changed, 1502 insertions(+), 524 deletions(-).

The main changes are:

1) Add BTFGen support to bpftool which allows to use CO-RE in kernels without
   BTF info, from Mauricio Vásquez, Rafael David Tinoco, Lorenzo Fontana and
   Leonardo Di Donato. (Details: https://lpc.events/event/11/contributions/948/)

2) Prepare light skeleton to be used in both kernel module and user space
   and convert bpf_preload.ko to use light skeleton, from Alexei Starovoitov.

3) Rework bpftool's versioning scheme and align with libbpf's version number;
   also add linked libbpf version info to "bpftool version", from Quentin Monnet.

4) Add minimal C++ specific additions to bpftool's skeleton codegen to
   facilitate use of C skeletons in C++ applications, from Andrii Nakryiko.

5) Add BPF verifier sanity check whether relative offset on kfunc calls overflows
   desc->imm and reject the BPF program if the case, from Hou Tao.

6) Fix libbpf to use a dynamically allocated buffer for netlink messages to
   avoid receiving truncated messages on some archs, from Toke Høiland-Jørgensen.

7) Various follow-up fixes to the JIT bpf_prog_pack allocator, from Song Liu.

8) Various BPF selftest and vmtest.sh fixes, from Yucong Sun.

9) Fix bpftool pretty print handling on dumping map keys/values when no BTF
   is available, from Jiri Olsa and Yinjun Zhang.

10) Extend XDP frags selftest to check for invalid length, from Lorenzo Bianconi.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (29 commits)
  bpf: bpf_prog_pack: Set proper size before freeing ro_header
  selftests/bpf: Fix crash in core_reloc when bpftool btfgen fails
  selftests/bpf: Fix vmtest.sh to launch smp vm.
  libbpf: Fix memleak in libbpf_netlink_recv()
  bpftool: Fix C++ additions to skeleton
  bpftool: Fix pretty print dump for maps without BTF loaded
  selftests/bpf: Test "bpftool gen min_core_btf"
  bpftool: Gen min_core_btf explanation and examples
  bpftool: Implement btfgen_get_btf()
  bpftool: Implement "gen min_core_btf" logic
  bpftool: Add gen min_core_btf command
  libbpf: Expose bpf_core_{add,free}_cands() to bpftool
  libbpf: Split bpf_core_apply_relo()
  bpf: Reject kfunc calls that overflow insn->imm
  selftests/bpf: Add Skeleton templated wrapper as an example
  bpftool: Add C++-specific open/load/etc skeleton wrappers
  selftests/bpf: Fix GCC11 compiler warnings in -O2 mode
  bpftool: Fix the error when lookup in no-btf maps
  libbpf: Use dynamically allocated buffer when receiving netlink messages
  libbpf: Fix libbpf.map inheritance chain for LIBBPF_0.7.0
  ...
====================

Link: https://lore.kernel.org/r/20220217232027.29831-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

8 files changed, 354 insertions, 129 deletions

diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 8ecef1088ba2..927745b08014 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -1043,18 +1043,27 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	value = add_data(gen, pvalue, value_size);
 	key = add_data(gen, &zero, sizeof(zero));
 
-	/* if (map_desc[map_idx].initial_value)
-	 *    copy_from_user(value, initial_value, value_size);
+	/* if (map_desc[map_idx].initial_value) {
+	 *    if (ctx->flags & BPF_SKEL_KERNEL)
+	 *        bpf_probe_read_kernel(value, value_size, initial_value);
+	 *    else
+	 *        bpf_copy_from_user(value, value_size, initial_value);
+	 * }
 	 */
 	emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6,
 			      sizeof(struct bpf_loader_ctx) +
 			      sizeof(struct bpf_map_desc) * map_idx +
 			      offsetof(struct bpf_map_desc, initial_value)));
-	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 4));
+	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 8));
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
 					 0, 0, 0, value));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_2, value_size));
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6,
+			      offsetof(struct bpf_loader_ctx, flags)));
+	emit(gen, BPF_JMP_IMM(BPF_JSET, BPF_REG_0, BPF_SKEL_KERNEL, 2));
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user));
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 1));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
 
 	map_update_attr = add_data(gen, &attr, attr_size);
 	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2262bcdfee92..ad43b6ce825e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -5192,18 +5192,21 @@ size_t bpf_core_essential_name_len(const char *name)
 	return n;
 }
 
-static void bpf_core_free_cands(struct bpf_core_cand_list *cands)
+void bpf_core_free_cands(struct bpf_core_cand_list *cands)
 {
+	if (!cands)
+		return;
+
 	free(cands->cands);
 	free(cands);
 }
 
-static int bpf_core_add_cands(struct bpf_core_cand *local_cand,
-			      size_t local_essent_len,
-			      const struct btf *targ_btf,
-			      const char *targ_btf_name,
-			      int targ_start_id,
-			      struct bpf_core_cand_list *cands)
+int bpf_core_add_cands(struct bpf_core_cand *local_cand,
+		       size_t local_essent_len,
+		       const struct btf *targ_btf,
+		       const char *targ_btf_name,
+		       int targ_start_id,
+		       struct bpf_core_cand_list *cands)
 {
 	struct bpf_core_cand *new_cands, *cand;
 	const struct btf_type *t, *local_t;
@@ -5530,11 +5533,12 @@ static int record_relo_core(struct bpf_program *prog,
 	return 0;
 }
 
-static int bpf_core_apply_relo(struct bpf_program *prog,
-			       const struct bpf_core_relo *relo,
-			       int relo_idx,
-			       const struct btf *local_btf,
-			       struct hashmap *cand_cache)
+static int bpf_core_resolve_relo(struct bpf_program *prog,
+				 const struct bpf_core_relo *relo,
+				 int relo_idx,
+				 const struct btf *local_btf,
+				 struct hashmap *cand_cache,
+				 struct bpf_core_relo_res *targ_res)
 {
 	struct bpf_core_spec specs_scratch[3] = {};
 	const void *type_key = u32_as_hash_key(relo->type_id);
@@ -5543,20 +5547,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	const struct btf_type *local_type;
 	const char *local_name;
 	__u32 local_id = relo->type_id;
-	struct bpf_insn *insn;
-	int insn_idx, err;
-
-	if (relo->insn_off % BPF_INSN_SZ)
-		return -EINVAL;
-	insn_idx = relo->insn_off / BPF_INSN_SZ;
-	/* adjust insn_idx from section frame of reference to the local
-	 * program's frame of reference; (sub-)program code is not yet
-	 * relocated, so it's enough to just subtract in-section offset
-	 */
-	insn_idx = insn_idx - prog->sec_insn_off;
-	if (insn_idx >= prog->insns_cnt)
-		return -EINVAL;
-	insn = &prog->insns[insn_idx];
+	int err;
 
 	local_type = btf__type_by_id(local_btf, local_id);
 	if (!local_type)
@@ -5566,15 +5557,6 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	if (!local_name)
 		return -EINVAL;
 
-	if (prog->obj->gen_loader) {
-		const char *spec_str = btf__name_by_offset(local_btf, relo->access_str_off);
-
-		pr_debug("record_relo_core: prog %td insn[%d] %s %s %s final insn_idx %d\n",
-			prog - prog->obj->programs, relo->insn_off / 8,
-			btf_kind_str(local_type), local_name, spec_str, insn_idx);
-		return record_relo_core(prog, relo, insn_idx);
-	}
-
 	if (relo->kind != BPF_CORE_TYPE_ID_LOCAL &&
 	    !hashmap__find(cand_cache, type_key, (void **)&cands)) {
 		cands = bpf_core_find_cands(prog->obj, local_btf, local_id);
@@ -5591,19 +5573,21 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 		}
 	}
 
-	return bpf_core_apply_relo_insn(prog_name, insn, insn_idx, relo,
-					relo_idx, local_btf, cands, specs_scratch);
+	return bpf_core_calc_relo_insn(prog_name, relo, relo_idx, local_btf, cands, specs_scratch,
+				       targ_res);
 }
 
 static int
 bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 {
 	const struct btf_ext_info_sec *sec;
+	struct bpf_core_relo_res targ_res;
 	const struct bpf_core_relo *rec;
 	const struct btf_ext_info *seg;
 	struct hashmap_entry *entry;
 	struct hashmap *cand_cache = NULL;
 	struct bpf_program *prog;
+	struct bpf_insn *insn;
 	const char *sec_name;
 	int i, err = 0, insn_idx, sec_idx;
 
@@ -5654,6 +5638,8 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 			 sec_name, sec->num_info);
 
 		for_each_btf_ext_rec(seg, sec, i, rec) {
+			if (rec->insn_off % BPF_INSN_SZ)
+				return -EINVAL;
 			insn_idx = rec->insn_off / BPF_INSN_SZ;
 			prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx);
 			if (!prog) {
@@ -5668,12 +5654,38 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 			if (!prog->load)
 				continue;
 
-			err = bpf_core_apply_relo(prog, rec, i, obj->btf, cand_cache);
+			/* adjust insn_idx from section frame of reference to the local
+			 * program's frame of reference; (sub-)program code is not yet
+			 * relocated, so it's enough to just subtract in-section offset
+			 */
+			insn_idx = insn_idx - prog->sec_insn_off;
+			if (insn_idx >= prog->insns_cnt)
+				return -EINVAL;
+			insn = &prog->insns[insn_idx];
+
+			if (prog->obj->gen_loader) {
+				err = record_relo_core(prog, rec, insn_idx);
+				if (err) {
+					pr_warn("prog '%s': relo #%d: failed to record relocation: %d\n",
+						prog->name, i, err);
+					goto out;
+				}
+				continue;
+			}
+
+			err = bpf_core_resolve_relo(prog, rec, i, obj->btf, cand_cache, &targ_res);
 			if (err) {
 				pr_warn("prog '%s': relo #%d: failed to relocate: %d\n",
 					prog->name, i, err);
 				goto out;
 			}
+
+			err = bpf_core_patch_insn(prog->name, insn, insn_idx, rec, i, &targ_res);
+			if (err) {
+				pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n",
+					prog->name, i, insn_idx, err);
+				goto out;
+			}
 		}
 	}
 
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index aef6253a90c8..47e70c9058d9 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -438,4 +438,4 @@ LIBBPF_0.7.0 {
 		libbpf_probe_bpf_map_type;
 		libbpf_probe_bpf_prog_type;
 		libbpf_set_memlock_rlim_max;
-};
+} LIBBPF_0.6.0;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index bc86b82e90d1..4fda8bdf0a0d 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -529,4 +529,13 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
+/* The following two functions are exposed to bpftool */
+int bpf_core_add_cands(struct bpf_core_cand *local_cand,
+		       size_t local_essent_len,
+		       const struct btf *targ_btf,
+		       const char *targ_btf_name,
+		       int targ_start_id,
+		       struct bpf_core_cand_list *cands);
+void bpf_core_free_cands(struct bpf_core_cand_list *cands);
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index c39c37f99d5c..cbc8967d5402 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -87,29 +87,75 @@ enum {
 	NL_DONE,
 };
 
+static int netlink_recvmsg(int sock, struct msghdr *mhdr, int flags)
+{
+	int len;
+
+	do {
+		len = recvmsg(sock, mhdr, flags);
+	} while (len < 0 && (errno == EINTR || errno == EAGAIN));
+
+	if (len < 0)
+		return -errno;
+	return len;
+}
+
+static int alloc_iov(struct iovec *iov, int len)
+{
+	void *nbuf;
+
+	nbuf = realloc(iov->iov_base, len);
+	if (!nbuf)
+		return -ENOMEM;
+
+	iov->iov_base = nbuf;
+	iov->iov_len = len;
+	return 0;
+}
+
 static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 			       __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
 			       void *cookie)
 {
+	struct iovec iov = {};
+	struct msghdr mhdr = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
 	bool multipart = true;
 	struct nlmsgerr *err;
 	struct nlmsghdr *nh;
-	char buf[4096];
 	int len, ret;
 
+	ret = alloc_iov(&iov, 4096);
+	if (ret)
+		goto done;
+
 	while (multipart) {
 start:
 		multipart = false;
-		len = recv(sock, buf, sizeof(buf), 0);
+		len = netlink_recvmsg(sock, &mhdr, MSG_PEEK | MSG_TRUNC);
+		if (len < 0) {
+			ret = len;
+			goto done;
+		}
+
+		if (len > iov.iov_len) {
+			ret = alloc_iov(&iov, len);
+			if (ret)
+				goto done;
+		}
+
+		len = netlink_recvmsg(sock, &mhdr, 0);
 		if (len < 0) {
-			ret = -errno;
+			ret = len;
 			goto done;
 		}
 
 		if (len == 0)
 			break;
 
-		for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+		for (nh = (struct nlmsghdr *)iov.iov_base; NLMSG_OK(nh, len);
 		     nh = NLMSG_NEXT(nh, len)) {
 			if (nh->nlmsg_pid != nl_pid) {
 				ret = -LIBBPF_ERRNO__WRNGPID;
@@ -130,7 +176,8 @@ start:
 				libbpf_nla_dump_errormsg(nh);
 				goto done;
 			case NLMSG_DONE:
-				return 0;
+				ret = 0;
+				goto done;
 			default:
 				break;
 			}
@@ -142,15 +189,17 @@ start:
 				case NL_NEXT:
 					goto start;
 				case NL_DONE:
-					return 0;
+					ret = 0;
+					goto done;
 				default:
-					return ret;
+					goto done;
 				}
 			}
 		}
 	}
 	ret = 0;
 done:
+	free(iov.iov_base);
 	return ret;
 }
 
diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c
index 910865e29edc..f946f23eab20 100644
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -775,31 +775,6 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo,
 	return 0;
 }
 
-struct bpf_core_relo_res
-{
-	/* expected value in the instruction, unless validate == false */
-	__u32 orig_val;
-	/* new value that needs to be patched up to */
-	__u32 new_val;
-	/* relocation unsuccessful, poison instruction, but don't fail load */
-	bool poison;
-	/* some relocations can't be validated against orig_val */
-	bool validate;
-	/* for field byte offset relocations or the forms:
-	 *     *(T *)(rX + <off>) = rY
-	 *     rX = *(T *)(rY + <off>),
-	 * we remember original and resolved field size to adjust direct
-	 * memory loads of pointers and integers; this is necessary for 32-bit
-	 * host kernel architectures, but also allows to automatically
-	 * relocate fields that were resized from, e.g., u32 to u64, etc.
-	 */
-	bool fail_memsz_adjust;
-	__u32 orig_sz;
-	__u32 orig_type_id;
-	__u32 new_sz;
-	__u32 new_type_id;
-};
-
 /* Calculate original and target relocation values, given local and target
  * specs and relocation kind. These values are calculated for each candidate.
  * If there are multiple candidates, resulting values should all be consistent
@@ -951,9 +926,9 @@ static int insn_bytes_to_bpf_size(__u32 sz)
  * 5. *(T *)(rX + <off>) = rY, where T is one of {u8, u16, u32, u64};
  * 6. *(T *)(rX + <off>) = <imm>, where T is one of {u8, u16, u32, u64}.
  */
-static int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
-			       int insn_idx, const struct bpf_core_relo *relo,
-			       int relo_idx, const struct bpf_core_relo_res *res)
+int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
+			int insn_idx, const struct bpf_core_relo *relo,
+			int relo_idx, const struct bpf_core_relo_res *res)
 {
 	__u32 orig_val, new_val;
 	__u8 class;
@@ -1128,7 +1103,7 @@ static void bpf_core_dump_spec(const char *prog_name, int level, const struct bp
 }
 
 /*
- * CO-RE relocate single instruction.
+ * Calculate CO-RE relocation target result.
  *
  * The outline and important points of the algorithm:
  * 1. For given local type, find corresponding candidate target types.
@@ -1177,18 +1152,18 @@ static void bpf_core_dump_spec(const char *prog_name, int level, const struct bp
  *    between multiple relocations for the same type ID and is updated as some
  *    of the candidates are pruned due to structural incompatibility.
  */
-int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
-			     int insn_idx,
-			     const struct bpf_core_relo *relo,
-			     int relo_idx,
-			     const struct btf *local_btf,
-			     struct bpf_core_cand_list *cands,
-			     struct bpf_core_spec *specs_scratch)
+int bpf_core_calc_relo_insn(const char *prog_name,
+			    const struct bpf_core_relo *relo,
+			    int relo_idx,
+			    const struct btf *local_btf,
+			    struct bpf_core_cand_list *cands,
+			    struct bpf_core_spec *specs_scratch,
+			    struct bpf_core_relo_res *targ_res)
 {
 	struct bpf_core_spec *local_spec = &specs_scratch[0];
 	struct bpf_core_spec *cand_spec = &specs_scratch[1];
 	struct bpf_core_spec *targ_spec = &specs_scratch[2];
-	struct bpf_core_relo_res cand_res, targ_res;
+	struct bpf_core_relo_res cand_res;
 	const struct btf_type *local_type;
 	const char *local_name;
 	__u32 local_id;
@@ -1223,12 +1198,12 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 	/* TYPE_ID_LOCAL relo is special and doesn't need candidate search */
 	if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) {
 		/* bpf_insn's imm value could get out of sync during linking */
-		memset(&targ_res, 0, sizeof(targ_res));
-		targ_res.validate = false;
-		targ_res.poison = false;
-		targ_res.orig_val = local_spec->root_type_id;
-		targ_res.new_val = local_spec->root_type_id;
-		goto patch_insn;
+		memset(targ_res, 0, sizeof(*targ_res));
+		targ_res->validate = false;
+		targ_res->poison = false;
+		targ_res->orig_val = local_spec->root_type_id;
+		targ_res->new_val = local_spec->root_type_id;
+		return 0;
 	}
 
 	/* libbpf doesn't support candidate search for anonymous types */
@@ -1262,7 +1237,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 			return err;
 
 		if (j == 0) {
-			targ_res = cand_res;
+			*targ_res = cand_res;
 			*targ_spec = *cand_spec;
 		} else if (cand_spec->bit_offset != targ_spec->bit_offset) {
 			/* if there are many field relo candidates, they
@@ -1272,7 +1247,8 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 				prog_name, relo_idx, cand_spec->bit_offset,
 				targ_spec->bit_offset);
 			return -EINVAL;
-		} else if (cand_res.poison != targ_res.poison || cand_res.new_val != targ_res.new_val) {
+		} else if (cand_res.poison != targ_res->poison ||
+			   cand_res.new_val != targ_res->new_val) {
 			/* all candidates should result in the same relocation
 			 * decision and value, otherwise it's dangerous to
 			 * proceed due to ambiguity
@@ -1280,7 +1256,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 			pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %u != %s %u\n",
 				prog_name, relo_idx,
 				cand_res.poison ? "failure" : "success", cand_res.new_val,
-				targ_res.poison ? "failure" : "success", targ_res.new_val);
+				targ_res->poison ? "failure" : "success", targ_res->new_val);
 			return -EINVAL;
 		}
 
@@ -1314,19 +1290,10 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 			 prog_name, relo_idx);
 
 		/* calculate single target relo result explicitly */
-		err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, &targ_res);
+		err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, targ_res);
 		if (err)
 			return err;
 	}
 
-patch_insn:
-	/* bpf_core_patch_insn() should know how to handle missing targ_spec */
-	err = bpf_core_patch_insn(prog_name, insn, insn_idx, relo, relo_idx, &targ_res);
-	if (err) {
-		pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n",
-			prog_name, relo_idx, relo->insn_off / 8, err);
-		return -EINVAL;
-	}
-
 	return 0;
 }
diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h
index 17799819ad7c..a28bf3711ce2 100644
--- a/tools/lib/bpf/relo_core.h
+++ b/tools/lib/bpf/relo_core.h
@@ -44,14 +44,44 @@ struct bpf_core_spec {
 	__u32 bit_offset;
 };
 
-int bpf_core_apply_relo_insn(const char *prog_name,
-			     struct bpf_insn *insn, int insn_idx,
-			     const struct bpf_core_relo *relo, int relo_idx,
-			     const struct btf *local_btf,
-			     struct bpf_core_cand_list *cands,
-			     struct bpf_core_spec *specs_scratch);
+struct bpf_core_relo_res {
+	/* expected value in the instruction, unless validate == false */
+	__u32 orig_val;
+	/* new value that needs to be patched up to */
+	__u32 new_val;
+	/* relocation unsuccessful, poison instruction, but don't fail load */
+	bool poison;
+	/* some relocations can't be validated against orig_val */
+	bool validate;
+	/* for field byte offset relocations or the forms:
+	 *     *(T *)(rX + <off>) = rY
+	 *     rX = *(T *)(rY + <off>),
+	 * we remember original and resolved field size to adjust direct
+	 * memory loads of pointers and integers; this is necessary for 32-bit
+	 * host kernel architectures, but also allows to automatically
+	 * relocate fields that were resized from, e.g., u32 to u64, etc.
+	 */
+	bool fail_memsz_adjust;
+	__u32 orig_sz;
+	__u32 orig_type_id;
+	__u32 new_sz;
+	__u32 new_type_id;
+};
+
 int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
 			      const struct btf *targ_btf, __u32 targ_id);
 
 size_t bpf_core_essential_name_len(const char *name);
+
+int bpf_core_calc_relo_insn(const char *prog_name,
+			    const struct bpf_core_relo *relo, int relo_idx,
+			    const struct btf *local_btf,
+			    struct bpf_core_cand_list *cands,
+			    struct bpf_core_spec *specs_scratch,
+			    struct bpf_core_relo_res *targ_res);
+
+int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn,
+			int insn_idx, const struct bpf_core_relo *relo,
+			int relo_idx, const struct bpf_core_relo_res *res);
+
 #endif
diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h
index dcd3336512d4..bd6f4505e7b1 100644
--- a/tools/lib/bpf/skel_internal.h
+++ b/tools/lib/bpf/skel_internal.h
@@ -3,9 +3,19 @@
 #ifndef __SKEL_INTERNAL_H
 #define __SKEL_INTERNAL_H
 
+#ifdef __KERNEL__
+#include <linux/fdtable.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#else
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <sys/mman.h>
+#include <stdlib.h>
+#include "bpf.h"
+#endif
 
 #ifndef __NR_bpf
 # if defined(__mips__) && defined(_ABIO32)
@@ -25,24 +35,23 @@
  * requested during loader program generation.
  */
 struct bpf_map_desc {
-	union {
-		/* input for the loader prog */
-		struct {
-			__aligned_u64 initial_value;
-			__u32 max_entries;
-		};
-		/* output of the loader prog */
-		struct {
-			int map_fd;
-		};
-	};
+	/* output of the loader prog */
+	int map_fd;
+	/* input for the loader prog */
+	__u32 max_entries;
+	__aligned_u64 initial_value;
 };
 struct bpf_prog_desc {
 	int prog_fd;
 };
 
+enum {
+	BPF_SKEL_KERNEL = (1ULL << 0),
+};
+
 struct bpf_loader_ctx {
-	size_t sz;
+	__u32 sz;
+	__u32 flags;
 	__u32 log_level;
 	__u32 log_size;
 	__u64 log_buf;
@@ -57,12 +66,144 @@ struct bpf_load_and_run_opts {
 	const char *errstr;
 };
 
+long bpf_sys_bpf(__u32 cmd, void *attr, __u32 attr_size);
+
 static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 			  unsigned int size)
 {
+#ifdef __KERNEL__
+	return bpf_sys_bpf(cmd, attr, size);
+#else
 	return syscall(__NR_bpf, cmd, attr, size);
+#endif
+}
+
+#ifdef __KERNEL__
+static inline int close(int fd)
+{
+	return close_fd(fd);
+}
+
+static inline void *skel_alloc(size_t size)
+{
+	struct bpf_loader_ctx *ctx = kzalloc(size, GFP_KERNEL);
+
+	if (!ctx)
+		return NULL;
+	ctx->flags |= BPF_SKEL_KERNEL;
+	return ctx;
+}
+
+static inline void skel_free(const void *p)
+{
+	kfree(p);
+}
+
+/* skel->bss/rodata maps are populated the following way:
+ *
+ * For kernel use:
+ * skel_prep_map_data() allocates kernel memory that kernel module can directly access.
+ * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value.
+ * The loader program will perform probe_read_kernel() from maps.rodata.initial_value.
+ * skel_finalize_map_data() sets skel->rodata to point to actual value in a bpf map and
+ * does maps.rodata.initial_value = ~0ULL to signal skel_free_map_data() that kvfree
+ * is not nessary.
+ *
+ * For user space:
+ * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly.
+ * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value.
+ * The loader program will perform copy_from_user() from maps.rodata.initial_value.
+ * skel_finalize_map_data() remaps bpf array map value from the kernel memory into
+ * skel->rodata address.
+ *
+ * The "bpftool gen skeleton -L" command generates lskel.h that is suitable for
+ * both kernel and user space. The generated loader program does
+ * either bpf_probe_read_kernel() or bpf_copy_from_user() from initial_value
+ * depending on bpf_loader_ctx->flags.
+ */
+static inline void skel_free_map_data(void *p, __u64 addr, size_t sz)
+{
+	if (addr != ~0ULL)
+		kvfree(p);
+	/* When addr == ~0ULL the 'p' points to
+	 * ((struct bpf_array *)map)->value. See skel_finalize_map_data.
+	 */
 }
 
+static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz)
+{
+	void *addr;
+
+	addr = kvmalloc(val_sz, GFP_KERNEL);
+	if (!addr)
+		return NULL;
+	memcpy(addr, val, val_sz);
+	return addr;
+}
+
+static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd)
+{
+	struct bpf_map *map;
+	void *addr = NULL;
+
+	kvfree((void *) (long) *init_val);
+	*init_val = ~0ULL;
+
+	/* At this point bpf_load_and_run() finished without error and
+	 * 'fd' is a valid bpf map FD. All sanity checks below should succeed.
+	 */
+	map = bpf_map_get(fd);
+	if (IS_ERR(map))
+		return NULL;
+	if (map->map_type != BPF_MAP_TYPE_ARRAY)
+		goto out;
+	addr = ((struct bpf_array *)map)->value;
+	/* the addr stays valid, since FD is not closed */
+out:
+	bpf_map_put(map);
+	return addr;
+}
+
+#else
+
+static inline void *skel_alloc(size_t size)
+{
+	return calloc(1, size);
+}
+
+static inline void skel_free(void *p)
+{
+	free(p);
+}
+
+static inline void skel_free_map_data(void *p, __u64 addr, size_t sz)
+{
+	munmap(p, sz);
+}
+
+static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz)
+{
+	void *addr;
+
+	addr = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
+		    MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (addr == (void *) -1)
+		return NULL;
+	memcpy(addr, val, val_sz);
+	return addr;
+}
+
+static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd)
+{
+	void *addr;
+
+	addr = mmap((void *) (long) *init_val, mmap_sz, flags, MAP_SHARED | MAP_FIXED, fd, 0);
+	if (addr == (void *) -1)
+		return NULL;
+	return addr;
+}
+#endif
+
 static inline int skel_closenz(int fd)
 {
 	if (fd > 0)
@@ -136,22 +277,28 @@ static inline int skel_link_create(int prog_fd, int target_fd,
 	return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz);
 }
 
+#ifdef __KERNEL__
+#define set_err
+#else
+#define set_err err = -errno
+#endif
+
 static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 {
 	int map_fd = -1, prog_fd = -1, key = 0, err;
 	union bpf_attr attr;
 
-	map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1);
+	err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1);
 	if (map_fd < 0) {
 		opts->errstr = "failed to create loader map";
-		err = -errno;
+		set_err;
 		goto out;
 	}
 
 	err = skel_map_update_elem(map_fd, &key, opts->data, 0);
 	if (err < 0) {
 		opts->errstr = "failed to update loader map";
-		err = -errno;
+		set_err;
 		goto out;
 	}
 
@@ -166,10 +313,10 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 	attr.log_size = opts->ctx->log_size;
 	attr.log_buf = opts->ctx->log_buf;
 	attr.prog_flags = BPF_F_SLEEPABLE;
-	prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	err = prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 	if (prog_fd < 0) {
 		opts->errstr = "failed to load loader prog";
-		err = -errno;
+		set_err;
 		goto out;
 	}
 
@@ -181,10 +328,12 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 	if (err < 0 || (int)attr.test.retval < 0) {
 		opts->errstr = "failed to execute loader prog";
 		if (err < 0) {
-			err = -errno;
+			set_err;
 		} else {
 			err = (int)attr.test.retval;
+#ifndef __KERNEL__
 			errno = -err;
+#endif
 		}
 		goto out;
 	}