Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Andrii Nakryiko says:

====================
bpf-next 2022-11-11

We've added 49 non-merge commits during the last 9 day(s) which contain
a total of 68 files changed, 3592 insertions(+), 1371 deletions(-).

The main changes are:

1) Veristat tool improvements to support custom filtering, sorting, and replay
   of results, from Andrii Nakryiko.

2) BPF verifier precision tracking fixes and improvements,
   from Andrii Nakryiko.

3) Lots of new BPF documentation for various BPF maps, from Dave Tucker,
   Donald Hunter, Maryam Tahhan, Bagas Sanjaya.

4) BTF dedup improvements and libbpf's hashmap interface clean ups, from
   Eduard Zingerman.

5) Fix veth driver panic if XDP program is attached before veth_open, from
   John Fastabend.

6) BPF verifier clean ups and fixes in preparation for follow up features,
   from Kumar Kartikeya Dwivedi.

7) Add access to hwtstamp field from BPF sockops programs,
   from Martin KaFai Lau.

8) Various fixes for BPF selftests and samples, from Artem Savkov,
   Domenico Cerasuolo, Kang Minchul, Rong Tao, Yang Jihong.

9) Fix redirection to tunneling device logic, preventing skb->len == 0, from
   Stanislav Fomichev.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (49 commits)
  selftests/bpf: fix veristat's singular file-or-prog filter
  selftests/bpf: Test skops->skb_hwtstamp
  selftests/bpf: Fix incorrect ASSERT in the tcp_hdr_options test
  bpf: Add hwtstamp field for the sockops prog
  selftests/bpf: Fix xdp_synproxy compilation failure in 32-bit arch
  bpf, docs: Document BPF_MAP_TYPE_ARRAY
  docs/bpf: Document BPF map types QUEUE and STACK
  docs/bpf: Document BPF ARRAY_OF_MAPS and HASH_OF_MAPS
  docs/bpf: Document BPF_MAP_TYPE_CPUMAP map
  docs/bpf: Document BPF_MAP_TYPE_LPM_TRIE map
  libbpf: Hashmap.h update to fix build issues using LLVM14
  bpf: veth driver panics when xdp prog attached before veth_open
  selftests: Fix test group SKIPPED result
  selftests/bpf: Tests for btf_dedup_resolve_fwds
  libbpf: Resolve unambigous forward declarations
  libbpf: Hashmap interface update to allow both long and void* keys/values
  samples/bpf: Fix sockex3 error: Missing BPF prog type
  selftests/bpf: Fix u32 variable compared with less than zero
  Documentation: bpf: Escape underscore in BPF type name prefix
  selftests/bpf: Use consistent build-id type for liburandom_read.so
  ...
====================

Link: https://lore.kernel.org/r/20221111233733.1088228-1-andrii@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

42 files changed, 1689 insertions, 637 deletions

diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index 68a70ac03c80..b87e4a7fd689 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -815,8 +815,7 @@ build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type,
 		if (!btf_id)
 			continue;
 
-		err = hashmap__append(tab, u32_as_hash_field(btf_id),
-				      u32_as_hash_field(id));
+		err = hashmap__append(tab, btf_id, id);
 		if (err) {
 			p_err("failed to append entry to hashmap for BTF ID %u, object ID %u: %s",
 			      btf_id, id, strerror(-err));
@@ -875,17 +874,13 @@ show_btf_plain(struct bpf_btf_info *info, int fd,
 	printf("size %uB", info->btf_size);
 
 	n = 0;
-	hashmap__for_each_key_entry(btf_prog_table, entry,
-				    u32_as_hash_field(info->id)) {
-		printf("%s%u", n++ == 0 ? "  prog_ids " : ",",
-		       hash_field_as_u32(entry->value));
+	hashmap__for_each_key_entry(btf_prog_table, entry, info->id) {
+		printf("%s%lu", n++ == 0 ? "  prog_ids " : ",", entry->value);
 	}
 
 	n = 0;
-	hashmap__for_each_key_entry(btf_map_table, entry,
-				    u32_as_hash_field(info->id)) {
-		printf("%s%u", n++ == 0 ? "  map_ids " : ",",
-		       hash_field_as_u32(entry->value));
+	hashmap__for_each_key_entry(btf_map_table, entry, info->id) {
+		printf("%s%lu", n++ == 0 ? "  map_ids " : ",", entry->value);
 	}
 
 	emit_obj_refs_plain(refs_table, info->id, "\n\tpids ");
@@ -907,17 +902,15 @@ show_btf_json(struct bpf_btf_info *info, int fd,
 
 	jsonw_name(json_wtr, "prog_ids");
 	jsonw_start_array(json_wtr);	/* prog_ids */
-	hashmap__for_each_key_entry(btf_prog_table, entry,
-				    u32_as_hash_field(info->id)) {
-		jsonw_uint(json_wtr, hash_field_as_u32(entry->value));
+	hashmap__for_each_key_entry(btf_prog_table, entry, info->id) {
+		jsonw_uint(json_wtr, entry->value);
 	}
 	jsonw_end_array(json_wtr);	/* prog_ids */
 
 	jsonw_name(json_wtr, "map_ids");
 	jsonw_start_array(json_wtr);	/* map_ids */
-	hashmap__for_each_key_entry(btf_map_table, entry,
-				    u32_as_hash_field(info->id)) {
-		jsonw_uint(json_wtr, hash_field_as_u32(entry->value));
+	hashmap__for_each_key_entry(btf_map_table, entry, info->id) {
+		jsonw_uint(json_wtr, entry->value);
 	}
 	jsonw_end_array(json_wtr);	/* map_ids */
 
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 653c130a0aaa..c90b756945e3 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -497,7 +497,7 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb,
 		goto out_close;
 	}
 
-	err = hashmap__append(build_fn_table, u32_as_hash_field(pinned_info.id), path);
+	err = hashmap__append(build_fn_table, pinned_info.id, path);
 	if (err) {
 		p_err("failed to append entry to hashmap for ID %u, path '%s': %s",
 		      pinned_info.id, path, strerror(errno));
@@ -548,7 +548,7 @@ void delete_pinned_obj_table(struct hashmap *map)
 		return;
 
 	hashmap__for_each_entry(map, entry, bkt)
-		free(entry->value);
+		free(entry->pvalue);
 
 	hashmap__free(map);
 }
@@ -1044,12 +1044,12 @@ int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
 	return fd;
 }
 
-size_t hash_fn_for_key_as_id(const void *key, void *ctx)
+size_t hash_fn_for_key_as_id(long key, void *ctx)
 {
-	return (size_t)key;
+	return key;
 }
 
-bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx)
+bool equal_fn_for_key_as_id(long k1, long k2, void *ctx)
 {
 	return k1 == k2;
 }
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index cf8b4e525c88..01bb8d8f5568 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -1660,21 +1660,16 @@ struct btfgen_info {
 	struct btf *marked_btf; /* btf structure used to mark used types */
 };
 
-static size_t btfgen_hash_fn(const void *key, void *ctx)
+static size_t btfgen_hash_fn(long key, void *ctx)
 {
-	return (size_t)key;
+	return key;
 }
 
-static bool btfgen_equal_fn(const void *k1, const void *k2, void *ctx)
+static bool btfgen_equal_fn(long k1, long k2, void *ctx)
 {
 	return k1 == k2;
 }
 
-static void *u32_as_hash_key(__u32 x)
-{
-	return (void *)(uintptr_t)x;
-}
-
 static void btfgen_free_info(struct btfgen_info *info)
 {
 	if (!info)
@@ -2086,18 +2081,18 @@ static int btfgen_record_obj(struct btfgen_info *info, const char *obj_path)
 			struct bpf_core_spec specs_scratch[3] = {};
 			struct bpf_core_relo_res targ_res = {};
 			struct bpf_core_cand_list *cands = NULL;
-			const void *type_key = u32_as_hash_key(relo->type_id);
 			const char *sec_name = btf__name_by_offset(btf, sec->sec_name_off);
 
 			if (relo->kind != BPF_CORE_TYPE_ID_LOCAL &&
-			    !hashmap__find(cand_cache, type_key, (void **)&cands)) {
+			    !hashmap__find(cand_cache, relo->type_id, &cands)) {
 				cands = btfgen_find_cands(btf, info->src_btf, relo->type_id);
 				if (!cands) {
 					err = -errno;
 					goto out;
 				}
 
-				err = hashmap__set(cand_cache, type_key, cands, NULL, NULL);
+				err = hashmap__set(cand_cache, relo->type_id, cands,
+						   NULL, NULL);
 				if (err)
 					goto out;
 			}
@@ -2120,7 +2115,7 @@ out:
 
 	if (!IS_ERR_OR_NULL(cand_cache)) {
 		hashmap__for_each_entry(cand_cache, entry, i) {
-			bpf_core_free_cands(entry->value);
+			bpf_core_free_cands(entry->pvalue);
 		}
 		hashmap__free(cand_cache);
 	}
diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 2863639706dd..6f4cfe01cad4 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -204,9 +204,8 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 
 		jsonw_name(json_wtr, "pinned");
 		jsonw_start_array(json_wtr);
-		hashmap__for_each_key_entry(link_table, entry,
-					    u32_as_hash_field(info->id))
-			jsonw_string(json_wtr, entry->value);
+		hashmap__for_each_key_entry(link_table, entry, info->id)
+			jsonw_string(json_wtr, entry->pvalue);
 		jsonw_end_array(json_wtr);
 	}
 
@@ -309,9 +308,8 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 	if (!hashmap__empty(link_table)) {
 		struct hashmap_entry *entry;
 
-		hashmap__for_each_key_entry(link_table, entry,
-					    u32_as_hash_field(info->id))
-			printf("\n\tpinned %s", (char *)entry->value);
+		hashmap__for_each_key_entry(link_table, entry, info->id)
+			printf("\n\tpinned %s", (char *)entry->pvalue);
 	}
 	emit_obj_refs_plain(refs_table, info->id, "\n\tpids ");
 
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 467d8472df0c..d4e8a1aef787 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -240,8 +240,8 @@ int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind,
 int print_all_levels(__maybe_unused enum libbpf_print_level level,
 		     const char *format, va_list args);
 
-size_t hash_fn_for_key_as_id(const void *key, void *ctx);
-bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx);
+size_t hash_fn_for_key_as_id(long key, void *ctx);
+bool equal_fn_for_key_as_id(long k1, long k2, void *ctx);
 
 /* bpf_attach_type_input_str - convert the provided attach type value into a
  * textual representation that we accept for input purposes.
@@ -257,16 +257,6 @@ bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx);
  */
 const char *bpf_attach_type_input_str(enum bpf_attach_type t);
 
-static inline void *u32_as_hash_field(__u32 x)
-{
-	return (void *)(uintptr_t)x;
-}
-
-static inline __u32 hash_field_as_u32(const void *x)
-{
-	return (__u32)(uintptr_t)x;
-}
-
 static inline bool hashmap__empty(struct hashmap *map)
 {
 	return map ? hashmap__size(map) == 0 : true;
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index f941ac5c7b73..d884070a2314 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -518,9 +518,8 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
 
 		jsonw_name(json_wtr, "pinned");
 		jsonw_start_array(json_wtr);
-		hashmap__for_each_key_entry(map_table, entry,
-					    u32_as_hash_field(info->id))
-			jsonw_string(json_wtr, entry->value);
+		hashmap__for_each_key_entry(map_table, entry, info->id)
+			jsonw_string(json_wtr, entry->pvalue);
 		jsonw_end_array(json_wtr);
 	}
 
@@ -595,9 +594,8 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
 	if (!hashmap__empty(map_table)) {
 		struct hashmap_entry *entry;
 
-		hashmap__for_each_key_entry(map_table, entry,
-					    u32_as_hash_field(info->id))
-			printf("\n\tpinned %s", (char *)entry->value);
+		hashmap__for_each_key_entry(map_table, entry, info->id)
+			printf("\n\tpinned %s", (char *)entry->pvalue);
 	}
 
 	if (frozen_str) {
diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c
index bb6c969a114a..00c77edb6331 100644
--- a/tools/bpf/bpftool/pids.c
+++ b/tools/bpf/bpftool/pids.c
@@ -36,8 +36,8 @@ static void add_ref(struct hashmap *map, struct pid_iter_entry *e)
 	int err, i;
 	void *tmp;
 
-	hashmap__for_each_key_entry(map, entry, u32_as_hash_field(e->id)) {
-		refs = entry->value;
+	hashmap__for_each_key_entry(map, entry, e->id) {
+		refs = entry->pvalue;
 
 		for (i = 0; i < refs->ref_cnt; i++) {
 			if (refs->refs[i].pid == e->pid)
@@ -81,7 +81,7 @@ static void add_ref(struct hashmap *map, struct pid_iter_entry *e)
 	refs->has_bpf_cookie = e->has_bpf_cookie;
 	refs->bpf_cookie = e->bpf_cookie;
 
-	err = hashmap__append(map, u32_as_hash_field(e->id), refs);
+	err = hashmap__append(map, e->id, refs);
 	if (err)
 		p_err("failed to append entry to hashmap for ID %u: %s",
 		      e->id, strerror(errno));
@@ -183,7 +183,7 @@ void delete_obj_refs_table(struct hashmap *map)
 		return;
 
 	hashmap__for_each_entry(map, entry, bkt) {
-		struct obj_refs *refs = entry->value;
+		struct obj_refs *refs = entry->pvalue;
 
 		free(refs->refs);
 		free(refs);
@@ -200,8 +200,8 @@ void emit_obj_refs_json(struct hashmap *map, __u32 id,
 	if (hashmap__empty(map))
 		return;
 
-	hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) {
-		struct obj_refs *refs = entry->value;
+	hashmap__for_each_key_entry(map, entry, id) {
+		struct obj_refs *refs = entry->pvalue;
 		int i;
 
 		if (refs->ref_cnt == 0)
@@ -232,8 +232,8 @@ void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix)
 	if (hashmap__empty(map))
 		return;
 
-	hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) {
-		struct obj_refs *refs = entry->value;
+	hashmap__for_each_key_entry(map, entry, id) {
+		struct obj_refs *refs = entry->pvalue;
 		int i;
 
 		if (refs->ref_cnt == 0)
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index a858b907da16..9d32ffb9f22e 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -486,9 +486,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 
 		jsonw_name(json_wtr, "pinned");
 		jsonw_start_array(json_wtr);
-		hashmap__for_each_key_entry(prog_table, entry,
-					    u32_as_hash_field(info->id))
-			jsonw_string(json_wtr, entry->value);
+		hashmap__for_each_key_entry(prog_table, entry, info->id)
+			jsonw_string(json_wtr, entry->pvalue);
 		jsonw_end_array(json_wtr);
 	}
 
@@ -561,9 +560,8 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 	if (!hashmap__empty(prog_table)) {
 		struct hashmap_entry *entry;
 
-		hashmap__for_each_key_entry(prog_table, entry,
-					    u32_as_hash_field(info->id))
-			printf("\n\tpinned %s", (char *)entry->value);
+		hashmap__for_each_key_entry(prog_table, entry, info->id)
+			printf("\n\tpinned %s", (char *)entry->pvalue);
 	}
 
 	if (info->btf_id)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 94659f6b3395..fb4c911d2a03 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6445,6 +6445,7 @@ struct bpf_sock_ops {
 				 * the outgoing header has not
 				 * been written yet.
 				 */
+	__u64 skb_hwtstamp;
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 675a0df5c840..3bd812bf88ff 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1559,15 +1559,15 @@ struct btf_pipe {
 static int btf_rewrite_str(__u32 *str_off, void *ctx)
 {
 	struct btf_pipe *p = ctx;
-	void *mapped_off;
+	long mapped_off;
 	int off, err;
 
 	if (!*str_off) /* nothing to do for empty strings */
 		return 0;
 
 	if (p->str_off_map &&
-	    hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) {
-		*str_off = (__u32)(long)mapped_off;
+	    hashmap__find(p->str_off_map, *str_off, &mapped_off)) {
+		*str_off = mapped_off;
 		return 0;
 	}
 
@@ -1579,7 +1579,7 @@ static int btf_rewrite_str(__u32 *str_off, void *ctx)
 	 * performing expensive string comparisons.
 	 */
 	if (p->str_off_map) {
-		err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off);
+		err = hashmap__append(p->str_off_map, *str_off, off);
 		if (err)
 			return err;
 	}
@@ -1630,8 +1630,8 @@ static int btf_rewrite_type_ids(__u32 *type_id, void *ctx)
 	return 0;
 }
 
-static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx);
-static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx);
+static size_t btf_dedup_identity_hash_fn(long key, void *ctx);
+static bool btf_dedup_equal_fn(long k1, long k2, void *ctx);
 
 int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 {
@@ -2881,6 +2881,7 @@ static int btf_dedup_strings(struct btf_dedup *d);
 static int btf_dedup_prim_types(struct btf_dedup *d);
 static int btf_dedup_struct_types(struct btf_dedup *d);
 static int btf_dedup_ref_types(struct btf_dedup *d);
+static int btf_dedup_resolve_fwds(struct btf_dedup *d);
 static int btf_dedup_compact_types(struct btf_dedup *d);
 static int btf_dedup_remap_types(struct btf_dedup *d);
 
@@ -2988,15 +2989,16 @@ static int btf_dedup_remap_types(struct btf_dedup *d);
  * Algorithm summary
  * =================
  *
- * Algorithm completes its work in 6 separate passes:
+ * Algorithm completes its work in 7 separate passes:
  *
  * 1. Strings deduplication.
  * 2. Primitive types deduplication (int, enum, fwd).
  * 3. Struct/union types deduplication.
- * 4. Reference types deduplication (pointers, typedefs, arrays, funcs, func
+ * 4. Resolve unambiguous forward declarations.
+ * 5. Reference types deduplication (pointers, typedefs, arrays, funcs, func
  *    protos, and const/volatile/restrict modifiers).
- * 5. Types compaction.
- * 6. Types remapping.
+ * 6. Types compaction.
+ * 7. Types remapping.
  *
  * Algorithm determines canonical type descriptor, which is a single
  * representative type for each truly unique type. This canonical type is the
@@ -3060,6 +3062,11 @@ int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts)
 		pr_debug("btf_dedup_struct_types failed:%d\n", err);
 		goto done;
 	}
+	err = btf_dedup_resolve_fwds(d);
+	if (err < 0) {
+		pr_debug("btf_dedup_resolve_fwds failed:%d\n", err);
+		goto done;
+	}
 	err = btf_dedup_ref_types(d);
 	if (err < 0) {
 		pr_debug("btf_dedup_ref_types failed:%d\n", err);
@@ -3126,12 +3133,11 @@ static long hash_combine(long h, long value)
 }
 
 #define for_each_dedup_cand(d, node, hash) \
-	hashmap__for_each_key_entry(d->dedup_table, node, (void *)hash)
+	hashmap__for_each_key_entry(d->dedup_table, node, hash)
 
 static int btf_dedup_table_add(struct btf_dedup *d, long hash, __u32 type_id)
 {
-	return hashmap__append(d->dedup_table,
-			       (void *)hash, (void *)(long)type_id);
+	return hashmap__append(d->dedup_table, hash, type_id);
 }
 
 static int btf_dedup_hypot_map_add(struct btf_dedup *d,
@@ -3178,17 +3184,17 @@ static void btf_dedup_free(struct btf_dedup *d)
 	free(d);
 }
 
-static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx)
+static size_t btf_dedup_identity_hash_fn(long key, void *ctx)
 {
-	return (size_t)key;
+	return key;
 }
 
-static size_t btf_dedup_collision_hash_fn(const void *key, void *ctx)
+static size_t btf_dedup_collision_hash_fn(long key, void *ctx)
 {
 	return 0;
 }
 
-static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx)
+static bool btf_dedup_equal_fn(long k1, long k2, void *ctx)
 {
 	return k1 == k2;
 }
@@ -3404,23 +3410,17 @@ static long btf_hash_enum(struct btf_type *t)
 {
 	long h;
 
-	/* don't hash vlen and enum members to support enum fwd resolving */
+	/* don't hash vlen, enum members and size to support enum fwd resolving */
 	h = hash_combine(0, t->name_off);
-	h = hash_combine(h, t->info & ~0xffff);
-	h = hash_combine(h, t->size);
 	return h;
 }
 
-/* Check structural equality of two ENUMs. */
-static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
+static bool btf_equal_enum_members(struct btf_type *t1, struct btf_type *t2)
 {
 	const struct btf_enum *m1, *m2;
 	__u16 vlen;
 	int i;
 
-	if (!btf_equal_common(t1, t2))
-		return false;
-
 	vlen = btf_vlen(t1);
 	m1 = btf_enum(t1);
 	m2 = btf_enum(t2);
@@ -3433,15 +3433,12 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
 	return true;
 }
 
-static bool btf_equal_enum64(struct btf_type *t1, struct btf_type *t2)
+static bool btf_equal_enum64_members(struct btf_type *t1, struct btf_type *t2)
 {
 	const struct btf_enum64 *m1, *m2;
 	__u16 vlen;
 	int i;
 
-	if (!btf_equal_common(t1, t2))
-		return false;
-
 	vlen = btf_vlen(t1);
 	m1 = btf_enum64(t1);
 	m2 = btf_enum64(t2);
@@ -3455,6 +3452,19 @@ static bool btf_equal_enum64(struct btf_type *t1, struct btf_type *t2)
 	return true;
 }
 
+/* Check structural equality of two ENUMs or ENUM64s. */
+static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
+{
+	if (!btf_equal_common(t1, t2))
+		return false;
+
+	/* t1 & t2 kinds are identical because of btf_equal_common */
+	if (btf_kind(t1) == BTF_KIND_ENUM)
+		return btf_equal_enum_members(t1, t2);
+	else
+		return btf_equal_enum64_members(t1, t2);
+}
+
 static inline bool btf_is_enum_fwd(struct btf_type *t)
 {
 	return btf_is_any_enum(t) && btf_vlen(t) == 0;
@@ -3464,21 +3474,14 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
 {
 	if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2))
 		return btf_equal_enum(t1, t2);
-	/* ignore vlen when comparing */
-	return t1->name_off == t2->name_off &&
-	       (t1->info & ~0xffff) == (t2->info & ~0xffff) &&
-	       t1->size == t2->size;
-}
-
-static bool btf_compat_enum64(struct btf_type *t1, struct btf_type *t2)
-{
-	if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2))
-		return btf_equal_enum64(t1, t2);
-
-	/* ignore vlen when comparing */
+	/* At this point either t1 or t2 or both are forward declarations, thus:
+	 * - skip comparing vlen because it is zero for forward declarations;
+	 * - skip comparing size to allow enum forward declarations
+	 *   to be compatible with enum64 full declarations;
+	 * - skip comparing kind for the same reason.
+	 */
 	return t1->name_off == t2->name_off &&
-	       (t1->info & ~0xffff) == (t2->info & ~0xffff) &&
-	       t1->size == t2->size;
+	       btf_is_any_enum(t1) && btf_is_any_enum(t2);
 }
 
 /*
@@ -3753,7 +3756,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_INT:
 		h = btf_hash_int_decl_tag(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_int_tag(t, cand)) {
 				new_id = cand_id;
@@ -3763,9 +3766,10 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		break;
 
 	case BTF_KIND_ENUM:
+	case BTF_KIND_ENUM64:
 		h = btf_hash_enum(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_enum(t, cand)) {
 				new_id = cand_id;
@@ -3783,32 +3787,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		}
 		break;
 
-	case BTF_KIND_ENUM64:
-		h = btf_hash_enum(t);
-		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
-			cand = btf_type_by_id(d->btf, cand_id);
-			if (btf_equal_enum64(t, cand)) {
-				new_id = cand_id;
-				break;
-			}
-			if (btf_compat_enum64(t, cand)) {
-				if (btf_is_enum_fwd(t)) {
-					/* resolve fwd to full enum */
-					new_id = cand_id;
-					break;
-				}
-				/* resolve canonical enum fwd to full enum */
-				d->map[cand_id] = type_id;
-			}
-		}
-		break;
-
 	case BTF_KIND_FWD:
 	case BTF_KIND_FLOAT:
 		h = btf_hash_common(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_common(t, cand)) {
 				new_id = cand_id;
@@ -4099,10 +4082,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return btf_equal_int_tag(cand_type, canon_type);
 
 	case BTF_KIND_ENUM:
-		return btf_compat_enum(cand_type, canon_type);
-
 	case BTF_KIND_ENUM64:
-		return btf_compat_enum64(cand_type, canon_type);
+		return btf_compat_enum(cand_type, canon_type);
 
 	case BTF_KIND_FWD:
 	case BTF_KIND_FLOAT:
@@ -4313,7 +4294,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 
 	h = btf_hash_struct(t);
 	for_each_dedup_cand(d, hash_entry, h) {
-		__u32 cand_id = (__u32)(long)hash_entry->value;
+		__u32 cand_id = hash_entry->value;
 		int eq;
 
 		/*
@@ -4418,7 +4399,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 
 		h = btf_hash_common(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_common(t, cand)) {
 				new_id = cand_id;
@@ -4435,7 +4416,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 
 		h = btf_hash_int_decl_tag(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_int_tag(t, cand)) {
 				new_id = cand_id;
@@ -4459,7 +4440,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 
 		h = btf_hash_array(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_array(t, cand)) {
 				new_id = cand_id;
@@ -4491,7 +4472,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 
 		h = btf_hash_fnproto(t);
 		for_each_dedup_cand(d, hash_entry, h) {
-			cand_id = (__u32)(long)hash_entry->value;
+			cand_id = hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_fnproto(t, cand)) {
 				new_id = cand_id;
@@ -4528,6 +4509,134 @@ static int btf_dedup_ref_types(struct btf_dedup *d)
 }
 
 /*
+ * Collect a map from type names to type ids for all canonical structs
+ * and unions. If the same name is shared by several canonical types
+ * use a special value 0 to indicate this fact.
+ */
+static int btf_dedup_fill_unique_names_map(struct btf_dedup *d, struct hashmap *names_map)
+{
+	__u32 nr_types = btf__type_cnt(d->btf);
+	struct btf_type *t;
+	__u32 type_id;
+	__u16 kind;
+	int err;
+
+	/*
+	 * Iterate over base and split module ids in order to get all
+	 * available structs in the map.
+	 */
+	for (type_id = 1; type_id < nr_types; ++type_id) {
+		t = btf_type_by_id(d->btf, type_id);
+		kind = btf_kind(t);
+
+		if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION)
+			continue;
+
+		/* Skip non-canonical types */
+		if (type_id != d->map[type_id])
+			continue;
+
+		err = hashmap__add(names_map, t->name_off, type_id);
+		if (err == -EEXIST)
+			err = hashmap__set(names_map, t->name_off, 0, NULL, NULL);
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int btf_dedup_resolve_fwd(struct btf_dedup *d, struct hashmap *names_map, __u32 type_id)
+{
+	struct btf_type *t = btf_type_by_id(d->btf, type_id);
+	enum btf_fwd_kind fwd_kind = btf_kflag(t);
+	__u16 cand_kind, kind = btf_kind(t);
+	struct btf_type *cand_t;
+	uintptr_t cand_id;
+
+	if (kind != BTF_KIND_FWD)
+		return 0;
+
+	/* Skip if this FWD already has a mapping */
+	if (type_id != d->map[type_id])
+		return 0;
+
+	if (!hashmap__find(names_map, t->name_off, &cand_id))
+		return 0;
+
+	/* Zero is a special value indicating that name is not unique */
+	if (!cand_id)
+		return 0;
+
+	cand_t = btf_type_by_id(d->btf, cand_id);
+	cand_kind = btf_kind(cand_t);
+	if ((cand_kind == BTF_KIND_STRUCT && fwd_kind != BTF_FWD_STRUCT) ||
+	    (cand_kind == BTF_KIND_UNION && fwd_kind != BTF_FWD_UNION))
+		return 0;
+
+	d->map[type_id] = cand_id;
+
+	return 0;
+}
+
+/*
+ * Resolve unambiguous forward declarations.
+ *
+ * The lion's share of all FWD declarations is resolved during
+ * `btf_dedup_struct_types` phase when different type graphs are
+ * compared against each other. However, if in some compilation unit a
+ * FWD declaration is not a part of a type graph compared against
+ * another type graph that declaration's canonical type would not be
+ * changed. Example:
+ *
+ * CU #1:
+ *
+ * struct foo;
+ * struct foo *some_global;
+ *
+ * CU #2:
+ *
+ * struct foo { int u; };
+ * struct foo *another_global;
+ *
+ * After `btf_dedup_struct_types` the BTF looks as follows:
+ *
+ * [1] STRUCT 'foo' size=4 vlen=1 ...
+ * [2] INT 'int' size=4 ...
+ * [3] PTR '(anon)' type_id=1
+ * [4] FWD 'foo' fwd_kind=struct
+ * [5] PTR '(anon)' type_id=4
+ *
+ * This pass assumes that such FWD declarations should be mapped to
+ * structs or unions with identical name in case if the name is not
+ * ambiguous.
+ */
+static int btf_dedup_resolve_fwds(struct btf_dedup *d)
+{
+	int i, err;
+	struct hashmap *names_map;
+
+	names_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL);
+	if (IS_ERR(names_map))
+		return PTR_ERR(names_map);
+
+	err = btf_dedup_fill_unique_names_map(d, names_map);
+	if (err < 0)
+		goto exit;
+
+	for (i = 0; i < d->btf->nr_types; i++) {
+		err = btf_dedup_resolve_fwd(d, names_map, d->btf->start_id + i);
+		if (err < 0)
+			break;
+	}
+
+exit:
+	hashmap__free(names_map);
+	return err;
+}
+
+/*
  * Compact types.
  *
  * After we established for each type its corresponding canonical representative
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index bf0cc0e986dd..12f7039e0ab2 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -117,14 +117,14 @@ struct btf_dump {
 	struct btf_dump_data *typed_dump;
 };
 
-static size_t str_hash_fn(const void *key, void *ctx)
+static size_t str_hash_fn(long key, void *ctx)
 {
-	return str_hash(key);
+	return str_hash((void *)key);
 }
 
-static bool str_equal_fn(const void *a, const void *b, void *ctx)
+static bool str_equal_fn(long a, long b, void *ctx)
 {
-	return strcmp(a, b) == 0;
+	return strcmp((void *)a, (void *)b) == 0;
 }
 
 static const char *btf_name_of(const struct btf_dump *d, __u32 name_off)
@@ -225,7 +225,7 @@ static void btf_dump_free_names(struct hashmap *map)
 	struct hashmap_entry *cur;
 
 	hashmap__for_each_entry(map, cur, bkt)
-		free((void *)cur->key);
+		free((void *)cur->pkey);
 
 	hashmap__free(map);
 }
@@ -1543,11 +1543,10 @@ static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map,
 	if (!new_name)
 		return 1;
 
-	hashmap__find(name_map, orig_name, (void **)&dup_cnt);
+	hashmap__find(name_map, orig_name, &dup_cnt);
 	dup_cnt++;
 
-	err = hashmap__set(name_map, new_name, (void *)dup_cnt,
-			   (const void **)&old_name, NULL);
+	err = hashmap__set(name_map, new_name, dup_cnt, &old_name, NULL);
 	if (err)
 		free(new_name);
 
diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c
index aeb09c288716..140ee4055676 100644
--- a/tools/lib/bpf/hashmap.c
+++ b/tools/lib/bpf/hashmap.c
@@ -128,7 +128,7 @@ static int hashmap_grow(struct hashmap *map)
 }
 
 static bool hashmap_find_entry(const struct hashmap *map,
-			       const void *key, size_t hash,
+			       const long key, size_t hash,
 			       struct hashmap_entry ***pprev,
 			       struct hashmap_entry **entry)
 {
@@ -151,18 +151,18 @@ static bool hashmap_find_entry(const struct hashmap *map,
 	return false;
 }
 
-int hashmap__insert(struct hashmap *map, const void *key, void *value,
-		    enum hashmap_insert_strategy strategy,
-		    const void **old_key, void **old_value)
+int hashmap_insert(struct hashmap *map, long key, long value,
+		   enum hashmap_insert_strategy strategy,
+		   long *old_key, long *old_value)
 {
 	struct hashmap_entry *entry;
 	size_t h;
 	int err;
 
 	if (old_key)
-		*old_key = NULL;
+		*old_key = 0;
 	if (old_value)
-		*old_value = NULL;
+		*old_value = 0;
 
 	h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
 	if (strategy != HASHMAP_APPEND &&
@@ -203,7 +203,7 @@ int hashmap__insert(struct hashmap *map, const void *key, void *value,
 	return 0;
 }
 
-bool hashmap__find(const struct hashmap *map, const void *key, void **value)
+bool hashmap_find(const struct hashmap *map, long key, long *value)
 {
 	struct hashmap_entry *entry;
 	size_t h;
@@ -217,8 +217,8 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value)
 	return true;
 }
 
-bool hashmap__delete(struct hashmap *map, const void *key,
-		     const void **old_key, void **old_value)
+bool hashmap_delete(struct hashmap *map, long key,
+		    long *old_key, long *old_value)
 {
 	struct hashmap_entry **pprev, *entry;
 	size_t h;
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index 10a4c4cd13cf..0a5bf1937a7c 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -40,12 +40,32 @@ static inline size_t str_hash(const char *s)
 	return h;
 }
 
-typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
-typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
+typedef size_t (*hashmap_hash_fn)(long key, void *ctx);
+typedef bool (*hashmap_equal_fn)(long key1, long key2, void *ctx);
 
+/*
+ * Hashmap interface is polymorphic, keys and values could be either
+ * long-sized integers or pointers, this is achieved as follows:
+ * - interface functions that operate on keys and values are hidden
+ *   behind auxiliary macros, e.g. hashmap_insert <-> hashmap__insert;
+ * - these auxiliary macros cast the key and value parameters as
+ *   long or long *, so the user does not have to specify the casts explicitly;
+ * - for pointer parameters (e.g. old_key) the size of the pointed
+ *   type is verified by hashmap_cast_ptr using _Static_assert;
+ * - when iterating using hashmap__for_each_* forms
+ *   hasmap_entry->key should be used for integer keys and
+ *   hasmap_entry->pkey should be used for pointer keys,
+ *   same goes for values.
+ */
 struct hashmap_entry {
-	const void *key;
-	void *value;
+	union {
+		long key;
+		const void *pkey;
+	};
+	union {
+		long value;
+		void *pvalue;
+	};
 	struct hashmap_entry *next;
 };
 
@@ -102,6 +122,13 @@ enum hashmap_insert_strategy {
 	HASHMAP_APPEND,
 };
 
+#define hashmap_cast_ptr(p) ({								\
+	_Static_assert((__builtin_constant_p((p)) ? (p) == NULL : 0) ||			\
+				sizeof(*(p)) == sizeof(long),				\
+		       #p " pointee should be a long-sized integer or a pointer");	\
+	(long *)(p);									\
+})
+
 /*
  * hashmap__insert() adds key/value entry w/ various semantics, depending on
  * provided strategy value. If a given key/value pair replaced already
@@ -109,42 +136,38 @@ enum hashmap_insert_strategy {
  * through old_key and old_value to allow calling code do proper memory
  * management.
  */
-int hashmap__insert(struct hashmap *map, const void *key, void *value,
-		    enum hashmap_insert_strategy strategy,
-		    const void **old_key, void **old_value);
+int hashmap_insert(struct hashmap *map, long key, long value,
+		   enum hashmap_insert_strategy strategy,
+		   long *old_key, long *old_value);
 
-static inline int hashmap__add(struct hashmap *map,
-			       const void *key, void *value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL);
-}
+#define hashmap__insert(map, key, value, strategy, old_key, old_value) \
+	hashmap_insert((map), (long)(key), (long)(value), (strategy),  \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
 
-static inline int hashmap__set(struct hashmap *map,
-			       const void *key, void *value,
-			       const void **old_key, void **old_value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_SET,
-			       old_key, old_value);
-}
+#define hashmap__add(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_ADD, NULL, NULL)
 
-static inline int hashmap__update(struct hashmap *map,
-				  const void *key, void *value,
-				  const void **old_key, void **old_value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_UPDATE,
-			       old_key, old_value);
-}
+#define hashmap__set(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_SET, (old_key), (old_value))
 
-static inline int hashmap__append(struct hashmap *map,
-				  const void *key, void *value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL);
-}
+#define hashmap__update(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_UPDATE, (old_key), (old_value))
+
+#define hashmap__append(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_APPEND, NULL, NULL)
+
+bool hashmap_delete(struct hashmap *map, long key, long *old_key, long *old_value);
+
+#define hashmap__delete(map, key, old_key, old_value)		       \
+	hashmap_delete((map), (long)(key),			       \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
 
-bool hashmap__delete(struct hashmap *map, const void *key,
-		     const void **old_key, void **old_value);
+bool hashmap_find(const struct hashmap *map, long key, long *value);
 
-bool hashmap__find(const struct hashmap *map, const void *key, void **value);
+#define hashmap__find(map, key, value) \
+	hashmap_find((map), (long)(key), hashmap_cast_ptr(value))
 
 /*
  * hashmap__for_each_entry - iterate over all entries in hashmap
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5d7819edf074..1d263885d635 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -5601,21 +5601,16 @@ int bpf_core_types_match(const struct btf *local_btf, __u32 local_id,
 	return __bpf_core_types_match(local_btf, local_id, targ_btf, targ_id, false, 32);
 }
 
-static size_t bpf_core_hash_fn(const void *key, void *ctx)
+static size_t bpf_core_hash_fn(const long key, void *ctx)
 {
-	return (size_t)key;
+	return key;
 }
 
-static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx)
+static bool bpf_core_equal_fn(const long k1, const long k2, void *ctx)
 {
 	return k1 == k2;
 }
 
-static void *u32_as_hash_key(__u32 x)
-{
-	return (void *)(uintptr_t)x;
-}
-
 static int record_relo_core(struct bpf_program *prog,
 			    const struct bpf_core_relo *core_relo, int insn_idx)
 {
@@ -5658,7 +5653,6 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 				 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);
 	struct bpf_core_cand_list *cands = NULL;
 	const char *prog_name = prog->name;
 	const struct btf_type *local_type;
@@ -5675,7 +5669,7 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 		return -EINVAL;
 
 	if (relo->kind != BPF_CORE_TYPE_ID_LOCAL &&
-	    !hashmap__find(cand_cache, type_key, (void **)&cands)) {
+	    !hashmap__find(cand_cache, local_id, &cands)) {
 		cands = bpf_core_find_cands(prog->obj, local_btf, local_id);
 		if (IS_ERR(cands)) {
 			pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld\n",
@@ -5683,7 +5677,7 @@ static int bpf_core_resolve_relo(struct bpf_program *prog,
 				local_name, PTR_ERR(cands));
 			return PTR_ERR(cands);
 		}
-		err = hashmap__set(cand_cache, type_key, cands, NULL, NULL);
+		err = hashmap__set(cand_cache, local_id, cands, NULL, NULL);
 		if (err) {
 			bpf_core_free_cands(cands);
 			return err;
@@ -5806,7 +5800,7 @@ out:
 
 	if (!IS_ERR_OR_NULL(cand_cache)) {
 		hashmap__for_each_entry(cand_cache, entry, i) {
-			bpf_core_free_cands(entry->value);
+			bpf_core_free_cands(entry->pvalue);
 		}
 		hashmap__free(cand_cache);
 	}
diff --git a/tools/lib/bpf/strset.c b/tools/lib/bpf/strset.c
index ea655318153f..2464bcbd04e0 100644
--- a/tools/lib/bpf/strset.c
+++ b/tools/lib/bpf/strset.c
@@ -19,19 +19,19 @@ struct strset {
 	struct hashmap *strs_hash;
 };
 
-static size_t strset_hash_fn(const void *key, void *ctx)
+static size_t strset_hash_fn(long key, void *ctx)
 {
 	const struct strset *s = ctx;
-	const char *str = s->strs_data + (long)key;
+	const char *str = s->strs_data + key;
 
 	return str_hash(str);
 }
 
-static bool strset_equal_fn(const void *key1, const void *key2, void *ctx)
+static bool strset_equal_fn(long key1, long key2, void *ctx)
 {
 	const struct strset *s = ctx;
-	const char *str1 = s->strs_data + (long)key1;
-	const char *str2 = s->strs_data + (long)key2;
+	const char *str1 = s->strs_data + key1;
+	const char *str2 = s->strs_data + key2;
 
 	return strcmp(str1, str2) == 0;
 }
@@ -67,7 +67,7 @@ struct strset *strset__new(size_t max_data_sz, const char *init_data, size_t ini
 			/* hashmap__add() returns EEXIST if string with the same
 			 * content already is in the hash map
 			 */
-			err = hashmap__add(hash, (void *)off, (void *)off);
+			err = hashmap__add(hash, off, off);
 			if (err == -EEXIST)
 				continue; /* duplicate */
 			if (err)
@@ -127,7 +127,7 @@ int strset__find_str(struct strset *set, const char *s)
 	new_off = set->strs_data_len;
 	memcpy(p, s, len);
 
-	if (hashmap__find(set->strs_hash, (void *)new_off, (void **)&old_off))
+	if (hashmap__find(set->strs_hash, new_off, &old_off))
 		return old_off;
 
 	return -ENOENT;
@@ -165,8 +165,8 @@ int strset__add_str(struct strset *set, const char *s)
 	 * contents doesn't exist already (HASHMAP_ADD strategy). If such
 	 * string exists, we'll get its offset in old_off (that's old_key).
 	 */
-	err = hashmap__insert(set->strs_hash, (void *)new_off, (void *)new_off,
-			      HASHMAP_ADD, (const void **)&old_off, NULL);
+	err = hashmap__insert(set->strs_hash, new_off, new_off,
+			      HASHMAP_ADD, &old_off, NULL);
 	if (err == -EEXIST)
 		return old_off; /* duplicated string, return existing offset */
 	if (err)
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index 28fa1b2283de..b8daae265f99 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -873,31 +873,27 @@ static void bpf_link_usdt_dealloc(struct bpf_link *link)
 	free(usdt_link);
 }
 
-static size_t specs_hash_fn(const void *key, void *ctx)
+static size_t specs_hash_fn(long key, void *ctx)
 {
-	const char *s = key;
-
-	return str_hash(s);
+	return str_hash((char *)key);
 }
 
-static bool specs_equal_fn(const void *key1, const void *key2, void *ctx)
+static bool specs_equal_fn(long key1, long key2, void *ctx)
 {
-	const char *s1 = key1;
-	const char *s2 = key2;
-
-	return strcmp(s1, s2) == 0;
+	return strcmp((char *)key1, (char *)key2) == 0;
 }
 
 static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash,
 			    struct bpf_link_usdt *link, struct usdt_target *target,
 			    int *spec_id, bool *is_new)
 {
-	void *tmp;
+	long tmp;
+	void *new_ids;
 	int err;
 
 	/* check if we already allocated spec ID for this spec string */
 	if (hashmap__find(specs_hash, target->spec_str, &tmp)) {
-		*spec_id = (long)tmp;
+		*spec_id = tmp;
 		*is_new = false;
 		return 0;
 	}
@@ -905,17 +901,17 @@ static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash
 	/* otherwise it's a new ID that needs to be set up in specs map and
 	 * returned back to usdt_manager when USDT link is detached
 	 */
-	tmp = libbpf_reallocarray(link->spec_ids, link->spec_cnt + 1, sizeof(*link->spec_ids));
-	if (!tmp)
+	new_ids = libbpf_reallocarray(link->spec_ids, link->spec_cnt + 1, sizeof(*link->spec_ids));
+	if (!new_ids)
 		return -ENOMEM;
-	link->spec_ids = tmp;
+	link->spec_ids = new_ids;
 
 	/* get next free spec ID, giving preference to free list, if not empty */
 	if (man->free_spec_cnt) {
 		*spec_id = man->free_spec_ids[man->free_spec_cnt - 1];
 
 		/* cache spec ID for current spec string for future lookups */
-		err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id);
+		err = hashmap__add(specs_hash, target->spec_str, *spec_id);
 		if (err)
 			 return err;
 
@@ -928,7 +924,7 @@ static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash
 		*spec_id = man->next_free_spec_id;
 
 		/* cache spec ID for current spec string for future lookups */
-		err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id);
+		err = hashmap__add(specs_hash, target->spec_str, *spec_id);
 		if (err)
 			 return err;
 
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 6512f5e22045..c598f95aebf3 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -130,12 +130,9 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 			expr__find_ids("FOO + BAR + BAZ + BOZO", "FOO",
 					ctx) == 0);
 	TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 3);
-	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAR",
-						    (void **)&val_ptr));
-	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAZ",
-						    (void **)&val_ptr));
-	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BOZO",
-						    (void **)&val_ptr));
+	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAR", &val_ptr));
+	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BAZ", &val_ptr));
+	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "BOZO", &val_ptr));
 
 	expr__ctx_clear(ctx);
 	ctx->sctx.runtime = 3;
@@ -143,20 +140,16 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 			expr__find_ids("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@",
 					NULL, ctx) == 0);
 	TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2);
-	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT1,param=3@",
-						    (void **)&val_ptr));
-	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3@",
-						    (void **)&val_ptr));
+	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT1,param=3@", &val_ptr));
+	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3@", &val_ptr));
 
 	expr__ctx_clear(ctx);
 	TEST_ASSERT_VAL("find ids",
 			expr__find_ids("dash\\-event1 - dash\\-event2",
 				       NULL, ctx) == 0);
 	TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2);
-	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event1",
-						    (void **)&val_ptr));
-	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event2",
-						    (void **)&val_ptr));
+	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event1", &val_ptr));
+	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event2", &val_ptr));
 
 	/* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */
 	{
@@ -174,7 +167,7 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 		TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1);
 		TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids,
 							  smton ? "EVENT1" : "EVENT2",
-							  (void **)&val_ptr));
+							  &val_ptr));
 
 		expr__ctx_clear(ctx);
 		TEST_ASSERT_VAL("find ids",
@@ -183,7 +176,7 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 		TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 1);
 		TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids,
 							  corewide ? "EVENT1" : "EVENT2",
-							  (void **)&val_ptr));
+							  &val_ptr));
 
 	}
 	/* The expression is a constant 1.0 without needing to evaluate EVENT1. */
@@ -220,8 +213,7 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 			expr__find_ids("source_count(EVENT1)",
 			NULL, ctx) == 0);
 	TEST_ASSERT_VAL("source count", hashmap__size(ctx->ids) == 1);
-	TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1",
-							(void **)&val_ptr));
+	TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1", &val_ptr));
 
 	expr__ctx_free(ctx);
 
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 097e05c796ab..3c2ee55e75c7 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -986,10 +986,10 @@ static int metric_parse_fake(const char *str)
 	 */
 	i = 1;
 	hashmap__for_each_entry(ctx->ids, cur, bkt)
-		expr__add_id_val(ctx, strdup(cur->key), i++);
+		expr__add_id_val(ctx, strdup(cur->pkey), i++);
 
 	hashmap__for_each_entry(ctx->ids, cur, bkt) {
-		if (check_parse_fake(cur->key)) {
+		if (check_parse_fake(cur->pkey)) {
 			pr_err("check_parse_fake failed\n");
 			goto out;
 		}
@@ -1003,7 +1003,7 @@ static int metric_parse_fake(const char *str)
 		 */
 		i = 1024;
 		hashmap__for_each_entry(ctx->ids, cur, bkt)
-			expr__add_id_val(ctx, strdup(cur->key), i--);
+			expr__add_id_val(ctx, strdup(cur->pkey), i--);
 		if (expr__parse(&result, ctx, str)) {
 			pr_err("expr__parse failed\n");
 			ret = -1;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index f4adeccdbbcb..a5dbd71cb9ab 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -318,7 +318,7 @@ static void bpf_program_hash_free(void)
 		return;
 
 	hashmap__for_each_entry(bpf_program_hash, cur, bkt)
-		clear_prog_priv(cur->key, cur->value);
+		clear_prog_priv(cur->pkey, cur->pvalue);
 
 	hashmap__free(bpf_program_hash);
 	bpf_program_hash = NULL;
@@ -339,13 +339,12 @@ void bpf__clear(void)
 	bpf_map_hash_free();
 }
 
-static size_t ptr_hash(const void *__key, void *ctx __maybe_unused)
+static size_t ptr_hash(const long __key, void *ctx __maybe_unused)
 {
-	return (size_t) __key;
+	return __key;
 }
 
-static bool ptr_equal(const void *key1, const void *key2,
-			  void *ctx __maybe_unused)
+static bool ptr_equal(long key1, long key2, void *ctx __maybe_unused)
 {
 	return key1 == key2;
 }
@@ -1185,7 +1184,7 @@ static void bpf_map_hash_free(void)
 		return;
 
 	hashmap__for_each_entry(bpf_map_hash, cur, bkt)
-		bpf_map_priv__clear(cur->key, cur->value);
+		bpf_map_priv__clear(cur->pkey, cur->pvalue);
 
 	hashmap__free(bpf_map_hash);
 	bpf_map_hash = NULL;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 76605fde3507..9e8a1294c981 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3123,7 +3123,7 @@ void evsel__zero_per_pkg(struct evsel *evsel)
 
 	if (evsel->per_pkg_mask) {
 		hashmap__for_each_entry(evsel->per_pkg_mask, cur, bkt)
-			free((char *)cur->key);
+			free((void *)cur->pkey);
 
 		hashmap__clear(evsel->per_pkg_mask);
 	}
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index aaacf514dc09..2f05ecdcfe9a 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -46,7 +46,7 @@ struct expr_id_data {
 	} kind;
 };
 
-static size_t key_hash(const void *key, void *ctx __maybe_unused)
+static size_t key_hash(long key, void *ctx __maybe_unused)
 {
 	const char *str = (const char *)key;
 	size_t hash = 0;
@@ -59,8 +59,7 @@ static size_t key_hash(const void *key, void *ctx __maybe_unused)
 	return hash;
 }
 
-static bool key_equal(const void *key1, const void *key2,
-		    void *ctx __maybe_unused)
+static bool key_equal(long key1, long key2, void *ctx __maybe_unused)
 {
 	return !strcmp((const char *)key1, (const char *)key2);
 }
@@ -84,8 +83,8 @@ void ids__free(struct hashmap *ids)
 		return;
 
 	hashmap__for_each_entry(ids, cur, bkt) {
-		free((char *)cur->key);
-		free(cur->value);
+		free((void *)cur->pkey);
+		free((void *)cur->pvalue);
 	}
 
 	hashmap__free(ids);
@@ -97,8 +96,7 @@ int ids__insert(struct hashmap *ids, const char *id)
 	char *old_key = NULL;
 	int ret;
 
-	ret = hashmap__set(ids, id, data_ptr,
-			   (const void **)&old_key, (void **)&old_data);
+	ret = hashmap__set(ids, id, data_ptr, &old_key, &old_data);
 	if (ret)
 		free(data_ptr);
 	free(old_key);
@@ -127,8 +125,7 @@ struct hashmap *ids__union(struct hashmap *ids1, struct hashmap *ids2)
 		ids2 = tmp;
 	}
 	hashmap__for_each_entry(ids2, cur, bkt) {
-		ret = hashmap__set(ids1, cur->key, cur->value,
-				(const void **)&old_key, (void **)&old_data);
+		ret = hashmap__set(ids1, cur->key, cur->value, &old_key, &old_data);
 		free(old_key);
 		free(old_data);
 
@@ -169,8 +166,7 @@ int expr__add_id_val_source_count(struct expr_parse_ctx *ctx, const char *id,
 	data_ptr->val.source_count = source_count;
 	data_ptr->kind = EXPR_ID_DATA__VALUE;
 
-	ret = hashmap__set(ctx->ids, id, data_ptr,
-			   (const void **)&old_key, (void **)&old_data);
+	ret = hashmap__set(ctx->ids, id, data_ptr, &old_key, &old_data);
 	if (ret)
 		free(data_ptr);
 	free(old_key);
@@ -205,8 +201,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref)
 	data_ptr->ref.metric_expr = ref->metric_expr;
 	data_ptr->kind = EXPR_ID_DATA__REF;
 
-	ret = hashmap__set(ctx->ids, name, data_ptr,
-			   (const void **)&old_key, (void **)&old_data);
+	ret = hashmap__set(ctx->ids, name, data_ptr, &old_key, &old_data);
 	if (ret)
 		free(data_ptr);
 
@@ -221,7 +216,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref)
 int expr__get_id(struct expr_parse_ctx *ctx, const char *id,
 		 struct expr_id_data **data)
 {
-	return hashmap__find(ctx->ids, id, (void **)data) ? 0 : -1;
+	return hashmap__find(ctx->ids, id, data) ? 0 : -1;
 }
 
 bool expr__subset_of_ids(struct expr_parse_ctx *haystack,
@@ -232,7 +227,7 @@ bool expr__subset_of_ids(struct expr_parse_ctx *haystack,
 	struct expr_id_data *data;
 
 	hashmap__for_each_entry(needles->ids, cur, bkt) {
-		if (expr__get_id(haystack, cur->key, &data))
+		if (expr__get_id(haystack, cur->pkey, &data))
 			return false;
 	}
 	return true;
@@ -282,8 +277,7 @@ void expr__del_id(struct expr_parse_ctx *ctx, const char *id)
 	struct expr_id_data *old_val = NULL;
 	char *old_key = NULL;
 
-	hashmap__delete(ctx->ids, id,
-			(const void **)&old_key, (void **)&old_val);
+	hashmap__delete(ctx->ids, id, &old_key, &old_val);
 	free(old_key);
 	free(old_val);
 }
@@ -314,8 +308,8 @@ void expr__ctx_clear(struct expr_parse_ctx *ctx)
 	size_t bkt;
 
 	hashmap__for_each_entry(ctx->ids, cur, bkt) {
-		free((char *)cur->key);
-		free(cur->value);
+		free((void *)cur->pkey);
+		free(cur->pvalue);
 	}
 	hashmap__clear(ctx->ids);
 }
@@ -330,8 +324,8 @@ void expr__ctx_free(struct expr_parse_ctx *ctx)
 
 	free(ctx->sctx.user_requested_cpu_list);
 	hashmap__for_each_entry(ctx->ids, cur, bkt) {
-		free((char *)cur->key);
-		free(cur->value);
+		free((void *)cur->pkey);
+		free(cur->pvalue);
 	}
 	hashmap__free(ctx->ids);
 	free(ctx);
diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c
index aeb09c288716..140ee4055676 100644
--- a/tools/perf/util/hashmap.c
+++ b/tools/perf/util/hashmap.c
@@ -128,7 +128,7 @@ static int hashmap_grow(struct hashmap *map)
 }
 
 static bool hashmap_find_entry(const struct hashmap *map,
-			       const void *key, size_t hash,
+			       const long key, size_t hash,
 			       struct hashmap_entry ***pprev,
 			       struct hashmap_entry **entry)
 {
@@ -151,18 +151,18 @@ static bool hashmap_find_entry(const struct hashmap *map,
 	return false;
 }
 
-int hashmap__insert(struct hashmap *map, const void *key, void *value,
-		    enum hashmap_insert_strategy strategy,
-		    const void **old_key, void **old_value)
+int hashmap_insert(struct hashmap *map, long key, long value,
+		   enum hashmap_insert_strategy strategy,
+		   long *old_key, long *old_value)
 {
 	struct hashmap_entry *entry;
 	size_t h;
 	int err;
 
 	if (old_key)
-		*old_key = NULL;
+		*old_key = 0;
 	if (old_value)
-		*old_value = NULL;
+		*old_value = 0;
 
 	h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits);
 	if (strategy != HASHMAP_APPEND &&
@@ -203,7 +203,7 @@ int hashmap__insert(struct hashmap *map, const void *key, void *value,
 	return 0;
 }
 
-bool hashmap__find(const struct hashmap *map, const void *key, void **value)
+bool hashmap_find(const struct hashmap *map, long key, long *value)
 {
 	struct hashmap_entry *entry;
 	size_t h;
@@ -217,8 +217,8 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value)
 	return true;
 }
 
-bool hashmap__delete(struct hashmap *map, const void *key,
-		     const void **old_key, void **old_value)
+bool hashmap_delete(struct hashmap *map, long key,
+		    long *old_key, long *old_value)
 {
 	struct hashmap_entry **pprev, *entry;
 	size_t h;
diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h
index 10a4c4cd13cf..0a5bf1937a7c 100644
--- a/tools/perf/util/hashmap.h
+++ b/tools/perf/util/hashmap.h
@@ -40,12 +40,32 @@ static inline size_t str_hash(const char *s)
 	return h;
 }
 
-typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
-typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
+typedef size_t (*hashmap_hash_fn)(long key, void *ctx);
+typedef bool (*hashmap_equal_fn)(long key1, long key2, void *ctx);
 
+/*
+ * Hashmap interface is polymorphic, keys and values could be either
+ * long-sized integers or pointers, this is achieved as follows:
+ * - interface functions that operate on keys and values are hidden
+ *   behind auxiliary macros, e.g. hashmap_insert <-> hashmap__insert;
+ * - these auxiliary macros cast the key and value parameters as
+ *   long or long *, so the user does not have to specify the casts explicitly;
+ * - for pointer parameters (e.g. old_key) the size of the pointed
+ *   type is verified by hashmap_cast_ptr using _Static_assert;
+ * - when iterating using hashmap__for_each_* forms
+ *   hasmap_entry->key should be used for integer keys and
+ *   hasmap_entry->pkey should be used for pointer keys,
+ *   same goes for values.
+ */
 struct hashmap_entry {
-	const void *key;
-	void *value;
+	union {
+		long key;
+		const void *pkey;
+	};
+	union {
+		long value;
+		void *pvalue;
+	};
 	struct hashmap_entry *next;
 };
 
@@ -102,6 +122,13 @@ enum hashmap_insert_strategy {
 	HASHMAP_APPEND,
 };
 
+#define hashmap_cast_ptr(p) ({								\
+	_Static_assert((__builtin_constant_p((p)) ? (p) == NULL : 0) ||			\
+				sizeof(*(p)) == sizeof(long),				\
+		       #p " pointee should be a long-sized integer or a pointer");	\
+	(long *)(p);									\
+})
+
 /*
  * hashmap__insert() adds key/value entry w/ various semantics, depending on
  * provided strategy value. If a given key/value pair replaced already
@@ -109,42 +136,38 @@ enum hashmap_insert_strategy {
  * through old_key and old_value to allow calling code do proper memory
  * management.
  */
-int hashmap__insert(struct hashmap *map, const void *key, void *value,
-		    enum hashmap_insert_strategy strategy,
-		    const void **old_key, void **old_value);
+int hashmap_insert(struct hashmap *map, long key, long value,
+		   enum hashmap_insert_strategy strategy,
+		   long *old_key, long *old_value);
 
-static inline int hashmap__add(struct hashmap *map,
-			       const void *key, void *value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL);
-}
+#define hashmap__insert(map, key, value, strategy, old_key, old_value) \
+	hashmap_insert((map), (long)(key), (long)(value), (strategy),  \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
 
-static inline int hashmap__set(struct hashmap *map,
-			       const void *key, void *value,
-			       const void **old_key, void **old_value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_SET,
-			       old_key, old_value);
-}
+#define hashmap__add(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_ADD, NULL, NULL)
 
-static inline int hashmap__update(struct hashmap *map,
-				  const void *key, void *value,
-				  const void **old_key, void **old_value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_UPDATE,
-			       old_key, old_value);
-}
+#define hashmap__set(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_SET, (old_key), (old_value))
 
-static inline int hashmap__append(struct hashmap *map,
-				  const void *key, void *value)
-{
-	return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL);
-}
+#define hashmap__update(map, key, value, old_key, old_value) \
+	hashmap__insert((map), (key), (value), HASHMAP_UPDATE, (old_key), (old_value))
+
+#define hashmap__append(map, key, value) \
+	hashmap__insert((map), (key), (value), HASHMAP_APPEND, NULL, NULL)
+
+bool hashmap_delete(struct hashmap *map, long key, long *old_key, long *old_value);
+
+#define hashmap__delete(map, key, old_key, old_value)		       \
+	hashmap_delete((map), (long)(key),			       \
+		       hashmap_cast_ptr(old_key),		       \
+		       hashmap_cast_ptr(old_value))
 
-bool hashmap__delete(struct hashmap *map, const void *key,
-		     const void **old_key, void **old_value);
+bool hashmap_find(const struct hashmap *map, long key, long *value);
 
-bool hashmap__find(const struct hashmap *map, const void *key, void **value);
+#define hashmap__find(map, key, value) \
+	hashmap_find((map), (long)(key), hashmap_cast_ptr(value))
 
 /*
  * hashmap__for_each_entry - iterate over all entries in hashmap
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 4c98ac29ee13..6b3505b1b6ac 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -288,7 +288,7 @@ static int setup_metric_events(struct hashmap *ids,
 		 * combined or shared groups, this metric may not care
 		 * about this event.
 		 */
-		if (hashmap__find(ids, metric_id, (void **)&val_ptr)) {
+		if (hashmap__find(ids, metric_id, &val_ptr)) {
 			metric_events[matched_events++] = ev;
 
 			if (matched_events >= ids_size)
@@ -764,7 +764,7 @@ static int metricgroup__build_event_string(struct strbuf *events,
 #define RETURN_IF_NON_ZERO(x) do { if (x) return x; } while (0)
 
 	hashmap__for_each_entry(ctx->ids, cur, bkt) {
-		const char *sep, *rsep, *id = cur->key;
+		const char *sep, *rsep, *id = cur->pkey;
 		enum perf_tool_event ev;
 
 		pr_debug("found event %s\n", id);
@@ -945,14 +945,14 @@ static int resolve_metric(struct list_head *metric_list,
 	hashmap__for_each_entry(root_metric->pctx->ids, cur, bkt) {
 		struct pmu_event pe;
 
-		if (metricgroup__find_metric(cur->key, table, &pe)) {
+		if (metricgroup__find_metric(cur->pkey, table, &pe)) {
 			pending = realloc(pending,
 					(pending_cnt + 1) * sizeof(struct to_resolve));
 			if (!pending)
 				return -ENOMEM;
 
 			memcpy(&pending[pending_cnt].pe, &pe, sizeof(pe));
-			pending[pending_cnt].key = cur->key;
+			pending[pending_cnt].key = cur->pkey;
 			pending_cnt++;
 		}
 	}
@@ -1433,7 +1433,7 @@ static int build_combined_expr_ctx(const struct list_head *metric_list,
 	list_for_each_entry(m, metric_list, nd) {
 		if (m->has_constraint && !m->modifier) {
 			hashmap__for_each_entry(m->pctx->ids, cur, bkt) {
-				dup = strdup(cur->key);
+				dup = strdup(cur->pkey);
 				if (!dup) {
 					ret = -ENOMEM;
 					goto err_out;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 07b29fe272c7..0bf71b02aa06 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -398,7 +398,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
 
 		i = 0;
 		hashmap__for_each_entry(ctx->ids, cur, bkt) {
-			const char *metric_name = (const char *)cur->key;
+			const char *metric_name = cur->pkey;
 
 			found = false;
 			if (leader) {
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 8ec8bb4a9912..c0656f85bfa5 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -278,15 +278,14 @@ void evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
 	}
 }
 
-static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused)
+static size_t pkg_id_hash(long __key, void *ctx __maybe_unused)
 {
 	uint64_t *key = (uint64_t *) __key;
 
 	return *key & 0xffffffff;
 }
 
-static bool pkg_id_equal(const void *__key1, const void *__key2,
-			 void *ctx __maybe_unused)
+static bool pkg_id_equal(long __key1, long __key2, void *ctx __maybe_unused)
 {
 	uint64_t *key1 = (uint64_t *) __key1;
 	uint64_t *key2 = (uint64_t *) __key2;
@@ -347,11 +346,11 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
 		return -ENOMEM;
 
 	*key = (uint64_t)d << 32 | s;
-	if (hashmap__find(mask, (void *)key, NULL)) {
+	if (hashmap__find(mask, key, NULL)) {
 		*skip = true;
 		free(key);
 	} else
-		ret = hashmap__add(mask, (void *)key, (void *)1);
+		ret = hashmap__add(mask, key, 1);
 
 	return ret;
 }
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 79edef1dbda4..f3cd17026ee5 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -182,14 +182,15 @@ endif
 $(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c
 	$(call msg,LIB,,$@)
 	$(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $^ $(LDLIBS)   \
-		     -fuse-ld=$(LLD) -Wl,-znoseparate-code -fPIC -shared -o $@
+		     -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \
+		     -fPIC -shared -o $@
 
 $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so
 	$(call msg,BINARY,,$@)
 	$(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \
 		     liburandom_read.so $(LDLIBS)			       \
-		     -fuse-ld=$(LLD) -Wl,-znoseparate-code		       \
-		     -Wl,-rpath=. -Wl,--build-id=sha1 -o $@
+		     -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \
+		     -Wl,-rpath=. -o $@
 
 $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c
 	$(call msg,SIGN-FILE,,$@)
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index a3352a64c067..10587a29b967 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -20,6 +20,25 @@ static inline unsigned int bpf_num_possible_cpus(void)
 	return possible_cpus;
 }
 
+/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst
+ * is zero-terminated string no matter what (unless sz == 0, in which case
+ * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs
+ * in what is returned. Given this is internal helper, it's trivial to extend
+ * this, when necessary. Use this instead of strncpy inside libbpf source code.
+ */
+static inline void bpf_strlcpy(char *dst, const char *src, size_t sz)
+{
+	size_t i;
+
+	if (sz == 0)
+		return;
+
+	sz--;
+	for (i = 0; i < sz && src[i]; i++)
+		dst[i] = src[i];
+	dst[i] = '\0';
+}
+
 #define __bpf_percpu_val_align	__attribute__((__aligned__(8)))
 
 #define BPF_DECLARE_PERCPU(type, name)				\
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index e914cc45b766..dd1aa5afcf5a 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -13,6 +13,7 @@
 #include <ftw.h>
 
 #include "cgroup_helpers.h"
+#include "bpf_util.h"
 
 /*
  * To avoid relying on the system setup, when setup_cgroup_env is called
@@ -77,7 +78,7 @@ static int __enable_controllers(const char *cgroup_path, const char *controllers
 		enable[len] = 0;
 		close(fd);
 	} else {
-		strncpy(enable, controllers, sizeof(enable));
+		bpf_strlcpy(enable, controllers, sizeof(enable));
 	}
 
 	snprintf(path, sizeof(path), "%s/cgroup.subtree_control", cgroup_path);
diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 970f09156eb4..4666f88f2bb4 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -2,7 +2,7 @@
 #include <test_progs.h>
 
 #define MAX_INSNS	512
-#define MAX_MATCHES	16
+#define MAX_MATCHES	24
 
 struct bpf_reg_match {
 	unsigned int line;
@@ -267,6 +267,7 @@ static struct bpf_align_test tests[] = {
 			 */
 			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
@@ -280,6 +281,7 @@ static struct bpf_align_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 4),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
@@ -311,44 +313,52 @@ static struct bpf_align_test tests[] = {
 			{15, "R4=pkt(id=1,off=18,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
 			{15, "R5=pkt(id=1,off=14,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
 			/* Variable offset is added to R5 packet pointer,
-			 * resulting in auxiliary alignment of 4.
+			 * resulting in auxiliary alignment of 4. To avoid BPF
+			 * verifier's precision backtracking logging
+			 * interfering we also have a no-op R4 = R5
+			 * instruction to validate R5 state. We also check
+			 * that R4 is what it should be in such case.
 			 */
-			{17, "R5_w=pkt(id=2,off=0,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{18, "R4_w=pkt(id=2,off=0,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{18, "R5_w=pkt(id=2,off=0,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
 			/* Constant offset is added to R5, resulting in
 			 * reg->off of 14.
 			 */
-			{18, "R5_w=pkt(id=2,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{19, "R5_w=pkt(id=2,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off
 			 * (14) which is 16.  Then the variable offset is 4-byte
 			 * aligned, so the total offset is 4-byte aligned and
 			 * meets the load's requirements.
 			 */
-			{23, "R4=pkt(id=2,off=18,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
-			{23, "R5=pkt(id=2,off=14,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
+			{24, "R4=pkt(id=2,off=18,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
+			{24, "R5=pkt(id=2,off=14,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
 			/* Constant offset is added to R5 packet pointer,
 			 * resulting in reg->off value of 14.
 			 */
-			{25, "R5_w=pkt(off=14,r=8"},
+			{26, "R5_w=pkt(off=14,r=8"},
 			/* Variable offset is added to R5, resulting in a
-			 * variable offset of (4n).
+			 * variable offset of (4n). See comment for insn #18
+			 * for R4 = R5 trick.
 			 */
-			{26, "R5_w=pkt(id=3,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{28, "R4_w=pkt(id=3,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{28, "R5_w=pkt(id=3,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
 			/* Constant is added to R5 again, setting reg->off to 18. */
-			{27, "R5_w=pkt(id=3,off=18,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{29, "R5_w=pkt(id=3,off=18,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
 			/* And once more we add a variable; resulting var_off
 			 * is still (4n), fixed offset is not changed.
 			 * Also, we create a new reg->id.
 			 */
-			{28, "R5_w=pkt(id=4,off=18,r=0,umax=2040,var_off=(0x0; 0x7fc)"},
+			{31, "R4_w=pkt(id=4,off=18,r=0,umax=2040,var_off=(0x0; 0x7fc)"},
+			{31, "R5_w=pkt(id=4,off=18,r=0,umax=2040,var_off=(0x0; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (18)
 			 * which is 20.  Then the variable offset is (4n), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{33, "R4=pkt(id=4,off=22,r=22,umax=2040,var_off=(0x0; 0x7fc)"},
-			{33, "R5=pkt(id=4,off=18,r=22,umax=2040,var_off=(0x0; 0x7fc)"},
+			{35, "R4=pkt(id=4,off=22,r=22,umax=2040,var_off=(0x0; 0x7fc)"},
+			{35, "R5=pkt(id=4,off=18,r=22,umax=2040,var_off=(0x0; 0x7fc)"},
 		},
 	},
 	{
@@ -681,6 +691,6 @@ void test_align(void)
 		if (!test__start_subtest(test->descr))
 			continue;
 
-		CHECK_FAIL(do_test_single(test));
+		ASSERT_OK(do_test_single(test), test->descr);
 	}
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 24dd6214394e..95a2b80f0d17 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -7133,7 +7133,7 @@ static struct btf_dedup_test dedup_tests[] = {
 				BTF_ENUM_ENC(NAME_NTH(4), 456),
 			/* [4] fwd enum 'e2' after full enum */
 			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4),
-			/* [5] incompatible fwd enum with different size */
+			/* [5] fwd enum with different size, size does not matter for fwd */
 			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1),
 			/* [6] incompatible full enum with different value */
 			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
@@ -7150,9 +7150,7 @@ static struct btf_dedup_test dedup_tests[] = {
 			/* [2] full enum 'e2' */
 			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
 				BTF_ENUM_ENC(NAME_NTH(4), 456),
-			/* [3] incompatible fwd enum with different size */
-			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1),
-			/* [4] incompatible full enum with different value */
+			/* [3] incompatible full enum with different value */
 			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
 				BTF_ENUM_ENC(NAME_NTH(2), 321),
 			BTF_END_RAW,
@@ -7611,7 +7609,263 @@ static struct btf_dedup_test dedup_tests[] = {
 		BTF_STR_SEC("\0e1\0e1_val"),
 	},
 },
-
+{
+	.descr = "dedup: enum of different size: no dedup",
+	.input = {
+		.raw_types = {
+			/* [1] enum 'e1' */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 1),
+			/* [2] enum 'e1' */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 2),
+				BTF_ENUM_ENC(NAME_NTH(2), 1),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0e1\0e1_val"),
+	},
+	.expect = {
+		.raw_types = {
+			/* [1] enum 'e1' */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 1),
+			/* [2] enum 'e1' */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 2),
+				BTF_ENUM_ENC(NAME_NTH(2), 1),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0e1\0e1_val"),
+	},
+},
+{
+	.descr = "dedup: enum fwd to enum64",
+	.input = {
+		.raw_types = {
+			/* [1] enum64 'e1' */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 8),
+				BTF_ENUM64_ENC(NAME_NTH(2), 1, 0),
+			/* [2] enum 'e1' fwd */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4),
+			/* [3] typedef enum 'e1' td */
+			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), 2),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0e1\0e1_val\0td"),
+	},
+	.expect = {
+		.raw_types = {
+			/* [1] enum64 'e1' */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 1), 8),
+				BTF_ENUM64_ENC(NAME_NTH(2), 1, 0),
+			/* [2] typedef enum 'e1' td */
+			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), 1),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0e1\0e1_val\0td"),
+	},
+},
+{
+	.descr = "dedup: enum64 fwd to enum",
+	.input = {
+		.raw_types = {
+			/* [1] enum 'e1' */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 1),
+			/* [2] enum64 'e1' fwd */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
+			/* [3] typedef enum 'e1' td */
+			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), 2),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0e1\0e1_val\0td"),
+	},
+	.expect = {
+		.raw_types = {
+			/* [1] enum 'e1' */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 1),
+			/* [2] typedef enum 'e1' td */
+			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), 1),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0e1\0e1_val\0td"),
+	},
+},
+{
+	.descr = "dedup: standalone fwd declaration struct",
+	/*
+	 * Verify that CU1:foo and CU2:foo would be unified and that
+	 * typedef/ptr would be updated to point to CU1:foo.
+	 *
+	 * // CU 1:
+	 * struct foo { int x; };
+	 *
+	 * // CU 2:
+	 * struct foo;
+	 * typedef struct foo *foo_ptr;
+	 */
+	.input = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 4),             /* [1] */
+			BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [2] */
+			/* CU 2 */
+			BTF_FWD_ENC(NAME_NTH(1), 0),                   /* [3] */
+			BTF_PTR_ENC(3),                                /* [4] */
+			BTF_TYPEDEF_ENC(NAME_NTH(3), 4),               /* [5] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0foo\0x\0foo_ptr"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 4),             /* [1] */
+			BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [2] */
+			BTF_PTR_ENC(1),                                /* [3] */
+			BTF_TYPEDEF_ENC(NAME_NTH(3), 3),               /* [4] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0foo\0x\0foo_ptr"),
+	},
+},
+{
+	.descr = "dedup: standalone fwd declaration union",
+	/*
+	 * Verify that CU1:foo and CU2:foo would be unified and that
+	 * typedef/ptr would be updated to point to CU1:foo.
+	 * Same as "dedup: standalone fwd declaration struct" but for unions.
+	 *
+	 * // CU 1:
+	 * union foo { int x; };
+	 *
+	 * // CU 2:
+	 * union foo;
+	 * typedef union foo *foo_ptr;
+	 */
+	.input = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_UNION_ENC(NAME_NTH(1), 1, 4),              /* [1] */
+			BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [2] */
+			/* CU 2 */
+			BTF_FWD_ENC(NAME_TBD, 1),                      /* [3] */
+			BTF_PTR_ENC(3),                                /* [4] */
+			BTF_TYPEDEF_ENC(NAME_NTH(3), 4),               /* [5] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0foo\0x\0foo_ptr"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_UNION_ENC(NAME_NTH(1), 1, 4),              /* [1] */
+			BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [2] */
+			BTF_PTR_ENC(1),                                /* [3] */
+			BTF_TYPEDEF_ENC(NAME_NTH(3), 3),               /* [4] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0foo\0x\0foo_ptr"),
+	},
+},
+{
+	.descr = "dedup: standalone fwd declaration wrong kind",
+	/*
+	 * Negative test for btf_dedup_resolve_fwds:
+	 * - CU1:foo is a struct, C2:foo is a union, thus CU2:foo is not deduped;
+	 * - typedef/ptr should remain unchanged as well.
+	 *
+	 * // CU 1:
+	 * struct foo { int x; };
+	 *
+	 * // CU 2:
+	 * union foo;
+	 * typedef union foo *foo_ptr;
+	 */
+	.input = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 4),             /* [1] */
+			BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [2] */
+			/* CU 2 */
+			BTF_FWD_ENC(NAME_NTH(3), 1),                   /* [3] */
+			BTF_PTR_ENC(3),                                /* [4] */
+			BTF_TYPEDEF_ENC(NAME_NTH(3), 4),               /* [5] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0foo\0x\0foo_ptr"),
+	},
+	.expect = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 4),             /* [1] */
+			BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [2] */
+			/* CU 2 */
+			BTF_FWD_ENC(NAME_NTH(3), 1),                   /* [3] */
+			BTF_PTR_ENC(3),                                /* [4] */
+			BTF_TYPEDEF_ENC(NAME_NTH(3), 4),               /* [5] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0foo\0x\0foo_ptr"),
+	},
+},
+{
+	.descr = "dedup: standalone fwd declaration name conflict",
+	/*
+	 * Negative test for btf_dedup_resolve_fwds:
+	 * - two candidates for CU2:foo dedup, thus it is unchanged;
+	 * - typedef/ptr should remain unchanged as well.
+	 *
+	 * // CU 1:
+	 * struct foo { int x; };
+	 *
+	 * // CU 2:
+	 * struct foo;
+	 * typedef struct foo *foo_ptr;
+	 *
+	 * // CU 3:
+	 * struct foo { int x; int y; };
+	 */
+	.input = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 4),             /* [1] */
+			BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [2] */
+			/* CU 2 */
+			BTF_FWD_ENC(NAME_NTH(1), 0),                   /* [3] */
+			BTF_PTR_ENC(3),                                /* [4] */
+			BTF_TYPEDEF_ENC(NAME_NTH(4), 4),               /* [5] */
+			/* CU 3 */
+			BTF_STRUCT_ENC(NAME_NTH(1), 2, 8),             /* [6] */
+			BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			BTF_MEMBER_ENC(NAME_NTH(3), 2, 0),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0foo\0x\0y\0foo_ptr"),
+	},
+	.expect = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 4),             /* [1] */
+			BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [2] */
+			/* CU 2 */
+			BTF_FWD_ENC(NAME_NTH(1), 0),                   /* [3] */
+			BTF_PTR_ENC(3),                                /* [4] */
+			BTF_TYPEDEF_ENC(NAME_NTH(4), 4),               /* [5] */
+			/* CU 3 */
+			BTF_STRUCT_ENC(NAME_NTH(1), 2, 8),             /* [6] */
+			BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			BTF_MEMBER_ENC(NAME_NTH(3), 2, 0),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0foo\0x\0y\0foo_ptr"),
+	},
+},
 };
 
 static int btf_type_size(const struct btf_type *t)
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
index 90aac437576d..d9024c7a892a 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
@@ -143,6 +143,10 @@ static void test_split_fwd_resolve() {
 	btf__add_struct(btf1, "s2", 4);			/* [5] struct s2 { */
 	btf__add_field(btf1, "f1", 1, 0, 0);		/*      int f1; */
 							/* } */
+	/* keep this not a part of type the graph to test btf_dedup_resolve_fwds */
+	btf__add_struct(btf1, "s3", 4);                 /* [6] struct s3 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*      int f1; */
+							/* } */
 
 	VALIDATE_RAW_BTF(
 		btf1,
@@ -153,20 +157,24 @@ static void test_split_fwd_resolve() {
 		"\t'f1' type_id=2 bits_offset=0\n"
 		"\t'f2' type_id=3 bits_offset=64",
 		"[5] STRUCT 's2' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[6] STRUCT 's3' size=4 vlen=1\n"
 		"\t'f1' type_id=1 bits_offset=0");
 
 	btf2 = btf__new_empty_split(btf1);
 	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
 		goto cleanup;
 
-	btf__add_int(btf2, "int", 4, BTF_INT_SIGNED);	/* [6] int */
-	btf__add_ptr(btf2, 10);				/* [7] ptr to struct s1 */
-	btf__add_fwd(btf2, "s2", BTF_FWD_STRUCT);	/* [8] fwd for struct s2 */
-	btf__add_ptr(btf2, 8);				/* [9] ptr to fwd struct s2 */
-	btf__add_struct(btf2, "s1", 16);		/* [10] struct s1 { */
-	btf__add_field(btf2, "f1", 7, 0, 0);		/*      struct s1 *f1; */
-	btf__add_field(btf2, "f2", 9, 64, 0);		/*      struct s2 *f2; */
+	btf__add_int(btf2, "int", 4, BTF_INT_SIGNED);	/* [7] int */
+	btf__add_ptr(btf2, 11);				/* [8] ptr to struct s1 */
+	btf__add_fwd(btf2, "s2", BTF_FWD_STRUCT);	/* [9] fwd for struct s2 */
+	btf__add_ptr(btf2, 9);				/* [10] ptr to fwd struct s2 */
+	btf__add_struct(btf2, "s1", 16);		/* [11] struct s1 { */
+	btf__add_field(btf2, "f1", 8, 0, 0);		/*      struct s1 *f1; */
+	btf__add_field(btf2, "f2", 10, 64, 0);		/*      struct s2 *f2; */
 							/* } */
+	btf__add_fwd(btf2, "s3", BTF_FWD_STRUCT);	/* [12] fwd for struct s3 */
+	btf__add_ptr(btf2, 12);				/* [13] ptr to struct s1 */
 
 	VALIDATE_RAW_BTF(
 		btf2,
@@ -178,13 +186,17 @@ static void test_split_fwd_resolve() {
 		"\t'f2' type_id=3 bits_offset=64",
 		"[5] STRUCT 's2' size=4 vlen=1\n"
 		"\t'f1' type_id=1 bits_offset=0",
-		"[6] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
-		"[7] PTR '(anon)' type_id=10",
-		"[8] FWD 's2' fwd_kind=struct",
-		"[9] PTR '(anon)' type_id=8",
-		"[10] STRUCT 's1' size=16 vlen=2\n"
-		"\t'f1' type_id=7 bits_offset=0\n"
-		"\t'f2' type_id=9 bits_offset=64");
+		"[6] STRUCT 's3' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[7] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[8] PTR '(anon)' type_id=11",
+		"[9] FWD 's2' fwd_kind=struct",
+		"[10] PTR '(anon)' type_id=9",
+		"[11] STRUCT 's1' size=16 vlen=2\n"
+		"\t'f1' type_id=8 bits_offset=0\n"
+		"\t'f2' type_id=10 bits_offset=64",
+		"[12] FWD 's3' fwd_kind=struct",
+		"[13] PTR '(anon)' type_id=12");
 
 	err = btf__dedup(btf2, NULL);
 	if (!ASSERT_OK(err, "btf_dedup"))
@@ -199,7 +211,10 @@ static void test_split_fwd_resolve() {
 		"\t'f1' type_id=2 bits_offset=0\n"
 		"\t'f2' type_id=3 bits_offset=64",
 		"[5] STRUCT 's2' size=4 vlen=1\n"
-		"\t'f1' type_id=1 bits_offset=0");
+		"\t'f1' type_id=1 bits_offset=0",
+		"[6] STRUCT 's3' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[7] PTR '(anon)' type_id=6");
 
 cleanup:
 	btf__free(btf2);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 24da335482d4..0ba2e8b9c6ac 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -791,11 +791,11 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d,
 	TEST_BTF_DUMP_DATA_OVER(btf, d, "struct", str, struct bpf_sock_ops,
 				sizeof(struct bpf_sock_ops) - 1,
 				"(struct bpf_sock_ops){\n\t.op = (__u32)1,\n",
-				{ .op = 1, .skb_tcp_flags = 2});
+				{ .op = 1, .skb_hwtstamp = 2});
 	TEST_BTF_DUMP_DATA_OVER(btf, d, "struct", str, struct bpf_sock_ops,
 				sizeof(struct bpf_sock_ops) - 1,
 				"(struct bpf_sock_ops){\n\t.op = (__u32)1,\n",
-				{ .op = 1, .skb_tcp_flags = 0});
+				{ .op = 1, .skb_hwtstamp = 0});
 }
 
 static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
diff --git a/tools/testing/selftests/bpf/prog_tests/hashmap.c b/tools/testing/selftests/bpf/prog_tests/hashmap.c
index 4747ab18f97f..d358a223fd2d 100644
--- a/tools/testing/selftests/bpf/prog_tests/hashmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/hashmap.c
@@ -7,17 +7,18 @@
  */
 #include "test_progs.h"
 #include "bpf/hashmap.h"
+#include <stddef.h>
 
 static int duration = 0;
 
-static size_t hash_fn(const void *k, void *ctx)
+static size_t hash_fn(long k, void *ctx)
 {
-	return (long)k;
+	return k;
 }
 
-static bool equal_fn(const void *a, const void *b, void *ctx)
+static bool equal_fn(long a, long b, void *ctx)
 {
-	return (long)a == (long)b;
+	return a == b;
 }
 
 static inline size_t next_pow_2(size_t n)
@@ -52,8 +53,8 @@ static void test_hashmap_generic(void)
 		return;
 
 	for (i = 0; i < ELEM_CNT; i++) {
-		const void *oldk, *k = (const void *)(long)i;
-		void *oldv, *v = (void *)(long)(1024 + i);
+		long oldk, k = i;
+		long oldv, v = 1024 + i;
 
 		err = hashmap__update(map, k, v, &oldk, &oldv);
 		if (CHECK(err != -ENOENT, "hashmap__update",
@@ -64,20 +65,18 @@ static void test_hashmap_generic(void)
 			err = hashmap__add(map, k, v);
 		} else {
 			err = hashmap__set(map, k, v, &oldk, &oldv);
-			if (CHECK(oldk != NULL || oldv != NULL, "check_kv",
-				  "unexpected k/v: %p=%p\n", oldk, oldv))
+			if (CHECK(oldk != 0 || oldv != 0, "check_kv",
+				  "unexpected k/v: %ld=%ld\n", oldk, oldv))
 				goto cleanup;
 		}
 
-		if (CHECK(err, "elem_add", "failed to add k/v %ld = %ld: %d\n",
-			       (long)k, (long)v, err))
+		if (CHECK(err, "elem_add", "failed to add k/v %ld = %ld: %d\n", k, v, err))
 			goto cleanup;
 
 		if (CHECK(!hashmap__find(map, k, &oldv), "elem_find",
-			  "failed to find key %ld\n", (long)k))
+			  "failed to find key %ld\n", k))
 			goto cleanup;
-		if (CHECK(oldv != v, "elem_val",
-			  "found value is wrong: %ld\n", (long)oldv))
+		if (CHECK(oldv != v, "elem_val", "found value is wrong: %ld\n", oldv))
 			goto cleanup;
 	}
 
@@ -91,8 +90,8 @@ static void test_hashmap_generic(void)
 
 	found_msk = 0;
 	hashmap__for_each_entry(map, entry, bkt) {
-		long k = (long)entry->key;
-		long v = (long)entry->value;
+		long k = entry->key;
+		long v = entry->value;
 
 		found_msk |= 1ULL << k;
 		if (CHECK(v - k != 1024, "check_kv",
@@ -104,8 +103,8 @@ static void test_hashmap_generic(void)
 		goto cleanup;
 
 	for (i = 0; i < ELEM_CNT; i++) {
-		const void *oldk, *k = (const void *)(long)i;
-		void *oldv, *v = (void *)(long)(256 + i);
+		long oldk, k = i;
+		long oldv, v = 256 + i;
 
 		err = hashmap__add(map, k, v);
 		if (CHECK(err != -EEXIST, "hashmap__add",
@@ -119,13 +118,13 @@ static void test_hashmap_generic(void)
 
 		if (CHECK(err, "elem_upd",
 			  "failed to update k/v %ld = %ld: %d\n",
-			  (long)k, (long)v, err))
+			  k, v, err))
 			goto cleanup;
 		if (CHECK(!hashmap__find(map, k, &oldv), "elem_find",
-			  "failed to find key %ld\n", (long)k))
+			  "failed to find key %ld\n", k))
 			goto cleanup;
 		if (CHECK(oldv != v, "elem_val",
-			  "found value is wrong: %ld\n", (long)oldv))
+			  "found value is wrong: %ld\n", oldv))
 			goto cleanup;
 	}
 
@@ -139,8 +138,8 @@ static void test_hashmap_generic(void)
 
 	found_msk = 0;
 	hashmap__for_each_entry_safe(map, entry, tmp, bkt) {
-		long k = (long)entry->key;
-		long v = (long)entry->value;
+		long k = entry->key;
+		long v = entry->value;
 
 		found_msk |= 1ULL << k;
 		if (CHECK(v - k != 256, "elem_check",
@@ -152,7 +151,7 @@ static void test_hashmap_generic(void)
 		goto cleanup;
 
 	found_cnt = 0;
-	hashmap__for_each_key_entry(map, entry, (void *)0) {
+	hashmap__for_each_key_entry(map, entry, 0) {
 		found_cnt++;
 	}
 	if (CHECK(!found_cnt, "found_cnt",
@@ -161,27 +160,25 @@ static void test_hashmap_generic(void)
 
 	found_msk = 0;
 	found_cnt = 0;
-	hashmap__for_each_key_entry_safe(map, entry, tmp, (void *)0) {
-		const void *oldk, *k;
-		void *oldv, *v;
+	hashmap__for_each_key_entry_safe(map, entry, tmp, 0) {
+		long oldk, k;
+		long oldv, v;
 
 		k = entry->key;
 		v = entry->value;
 
 		found_cnt++;
-		found_msk |= 1ULL << (long)k;
+		found_msk |= 1ULL << k;
 
 		if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), "elem_del",
-			  "failed to delete k/v %ld = %ld\n",
-			  (long)k, (long)v))
+			  "failed to delete k/v %ld = %ld\n", k, v))
 			goto cleanup;
 		if (CHECK(oldk != k || oldv != v, "check_old",
 			  "invalid deleted k/v: expected %ld = %ld, got %ld = %ld\n",
-			  (long)k, (long)v, (long)oldk, (long)oldv))
+			  k, v, oldk, oldv))
 			goto cleanup;
 		if (CHECK(hashmap__delete(map, k, &oldk, &oldv), "elem_del",
-			  "unexpectedly deleted k/v %ld = %ld\n",
-			  (long)oldk, (long)oldv))
+			  "unexpectedly deleted k/v %ld = %ld\n", oldk, oldv))
 			goto cleanup;
 	}
 
@@ -198,26 +195,24 @@ static void test_hashmap_generic(void)
 		goto cleanup;
 
 	hashmap__for_each_entry_safe(map, entry, tmp, bkt) {
-		const void *oldk, *k;
-		void *oldv, *v;
+		long oldk, k;
+		long oldv, v;
 
 		k = entry->key;
 		v = entry->value;
 
 		found_cnt++;
-		found_msk |= 1ULL << (long)k;
+		found_msk |= 1ULL << k;
 
 		if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), "elem_del",
-			  "failed to delete k/v %ld = %ld\n",
-			  (long)k, (long)v))
+			  "failed to delete k/v %ld = %ld\n", k, v))
 			goto cleanup;
 		if (CHECK(oldk != k || oldv != v, "elem_check",
 			  "invalid old k/v: expect %ld = %ld, got %ld = %ld\n",
-			  (long)k, (long)v, (long)oldk, (long)oldv))
+			  k, v, oldk, oldv))
 			goto cleanup;
 		if (CHECK(hashmap__delete(map, k, &oldk, &oldv), "elem_del",
-			  "unexpectedly deleted k/v %ld = %ld\n",
-			  (long)k, (long)v))
+			  "unexpectedly deleted k/v %ld = %ld\n", k, v))
 			goto cleanup;
 	}
 
@@ -235,7 +230,7 @@ static void test_hashmap_generic(void)
 	hashmap__for_each_entry(map, entry, bkt) {
 		CHECK(false, "elem_exists",
 		      "unexpected map entries left: %ld = %ld\n",
-		      (long)entry->key, (long)entry->value);
+		      entry->key, entry->value);
 		goto cleanup;
 	}
 
@@ -243,22 +238,107 @@ static void test_hashmap_generic(void)
 	hashmap__for_each_entry(map, entry, bkt) {
 		CHECK(false, "elem_exists",
 		      "unexpected map entries left: %ld = %ld\n",
-		      (long)entry->key, (long)entry->value);
+		      entry->key, entry->value);
+		goto cleanup;
+	}
+
+cleanup:
+	hashmap__free(map);
+}
+
+static size_t str_hash_fn(long a, void *ctx)
+{
+	return str_hash((char *)a);
+}
+
+static bool str_equal_fn(long a, long b, void *ctx)
+{
+	return strcmp((char *)a, (char *)b) == 0;
+}
+
+/* Verify that hashmap interface works with pointer keys and values */
+static void test_hashmap_ptr_iface(void)
+{
+	const char *key, *value, *old_key, *old_value;
+	struct hashmap_entry *cur;
+	struct hashmap *map;
+	int err, i, bkt;
+
+	map = hashmap__new(str_hash_fn, str_equal_fn, NULL);
+	if (CHECK(!map, "hashmap__new", "can't allocate hashmap\n"))
 		goto cleanup;
+
+#define CHECK_STR(fn, var, expected)					\
+	CHECK(strcmp(var, (expected)), (fn),				\
+	      "wrong value of " #var ": '%s' instead of '%s'\n", var, (expected))
+
+	err = hashmap__insert(map, "a", "apricot", HASHMAP_ADD, NULL, NULL);
+	if (CHECK(err, "hashmap__insert", "unexpected error: %d\n", err))
+		goto cleanup;
+
+	err = hashmap__insert(map, "a", "apple", HASHMAP_SET, &old_key, &old_value);
+	if (CHECK(err, "hashmap__insert", "unexpected error: %d\n", err))
+		goto cleanup;
+	CHECK_STR("hashmap__update", old_key, "a");
+	CHECK_STR("hashmap__update", old_value, "apricot");
+
+	err = hashmap__add(map, "b", "banana");
+	if (CHECK(err, "hashmap__add", "unexpected error: %d\n", err))
+		goto cleanup;
+
+	err = hashmap__set(map, "b", "breadfruit", &old_key, &old_value);
+	if (CHECK(err, "hashmap__set", "unexpected error: %d\n", err))
+		goto cleanup;
+	CHECK_STR("hashmap__set", old_key, "b");
+	CHECK_STR("hashmap__set", old_value, "banana");
+
+	err = hashmap__update(map, "b", "blueberry", &old_key, &old_value);
+	if (CHECK(err, "hashmap__update", "unexpected error: %d\n", err))
+		goto cleanup;
+	CHECK_STR("hashmap__update", old_key, "b");
+	CHECK_STR("hashmap__update", old_value, "breadfruit");
+
+	err = hashmap__append(map, "c", "cherry");
+	if (CHECK(err, "hashmap__append", "unexpected error: %d\n", err))
+		goto cleanup;
+
+	if (CHECK(!hashmap__delete(map, "c", &old_key, &old_value),
+		  "hashmap__delete", "expected to have entry for 'c'\n"))
+		goto cleanup;
+	CHECK_STR("hashmap__delete", old_key, "c");
+	CHECK_STR("hashmap__delete", old_value, "cherry");
+
+	CHECK(!hashmap__find(map, "b", &value), "hashmap__find", "can't find value for 'b'\n");
+	CHECK_STR("hashmap__find", value, "blueberry");
+
+	if (CHECK(!hashmap__delete(map, "b", NULL, NULL),
+		  "hashmap__delete", "expected to have entry for 'b'\n"))
+		goto cleanup;
+
+	i = 0;
+	hashmap__for_each_entry(map, cur, bkt) {
+		if (CHECK(i != 0, "hashmap__for_each_entry", "too many entries"))
+			goto cleanup;
+		key = cur->pkey;
+		value = cur->pvalue;
+		CHECK_STR("entry", key, "a");
+		CHECK_STR("entry", value, "apple");
+		i++;
 	}
+#undef CHECK_STR
 
 cleanup:
 	hashmap__free(map);
 }
 
-static size_t collision_hash_fn(const void *k, void *ctx)
+static size_t collision_hash_fn(long k, void *ctx)
 {
 	return 0;
 }
 
 static void test_hashmap_multimap(void)
 {
-	void *k1 = (void *)0, *k2 = (void *)1;
+	long k1 = 0, k2 = 1;
 	struct hashmap_entry *entry;
 	struct hashmap *map;
 	long found_msk;
@@ -273,23 +353,23 @@ static void test_hashmap_multimap(void)
 	 * [0] -> 1, 2, 4;
 	 * [1] -> 8, 16, 32;
 	 */
-	err = hashmap__append(map, k1, (void *)1);
+	err = hashmap__append(map, k1, 1);
 	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
 		goto cleanup;
-	err = hashmap__append(map, k1, (void *)2);
+	err = hashmap__append(map, k1, 2);
 	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
 		goto cleanup;
-	err = hashmap__append(map, k1, (void *)4);
+	err = hashmap__append(map, k1, 4);
 	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
 		goto cleanup;
 
-	err = hashmap__append(map, k2, (void *)8);
+	err = hashmap__append(map, k2, 8);
 	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
 		goto cleanup;
-	err = hashmap__append(map, k2, (void *)16);
+	err = hashmap__append(map, k2, 16);
 	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
 		goto cleanup;
-	err = hashmap__append(map, k2, (void *)32);
+	err = hashmap__append(map, k2, 32);
 	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
 		goto cleanup;
 
@@ -300,7 +380,7 @@ static void test_hashmap_multimap(void)
 	/* verify global iteration still works and sees all values */
 	found_msk = 0;
 	hashmap__for_each_entry(map, entry, bkt) {
-		found_msk |= (long)entry->value;
+		found_msk |= entry->value;
 	}
 	if (CHECK(found_msk != (1 << 6) - 1, "found_msk",
 		  "not all keys iterated: %lx\n", found_msk))
@@ -309,7 +389,7 @@ static void test_hashmap_multimap(void)
 	/* iterate values for key 1 */
 	found_msk = 0;
 	hashmap__for_each_key_entry(map, entry, k1) {
-		found_msk |= (long)entry->value;
+		found_msk |= entry->value;
 	}
 	if (CHECK(found_msk != (1 | 2 | 4), "found_msk",
 		  "invalid k1 values: %lx\n", found_msk))
@@ -318,7 +398,7 @@ static void test_hashmap_multimap(void)
 	/* iterate values for key 2 */
 	found_msk = 0;
 	hashmap__for_each_key_entry(map, entry, k2) {
-		found_msk |= (long)entry->value;
+		found_msk |= entry->value;
 	}
 	if (CHECK(found_msk != (8 | 16 | 32), "found_msk",
 		  "invalid k2 values: %lx\n", found_msk))
@@ -333,7 +413,7 @@ static void test_hashmap_empty()
 	struct hashmap_entry *entry;
 	int bkt;
 	struct hashmap *map;
-	void *k = (void *)0;
+	long k = 0;
 
 	/* force collisions */
 	map = hashmap__new(hash_fn, equal_fn, NULL);
@@ -374,4 +454,6 @@ void test_hashmap()
 		test_hashmap_multimap();
 	if (test__start_subtest("empty"))
 		test_hashmap_empty();
+	if (test__start_subtest("ptr_iface"))
+		test_hashmap_ptr_iface();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 287b3ac40227..eedbf1937fc4 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -312,12 +312,12 @@ static inline __u64 get_time_ns(void)
 	return (__u64) t.tv_sec * 1000000000 + t.tv_nsec;
 }
 
-static size_t symbol_hash(const void *key, void *ctx __maybe_unused)
+static size_t symbol_hash(long key, void *ctx __maybe_unused)
 {
 	return str_hash((const char *) key);
 }
 
-static bool symbol_equal(const void *key1, const void *key2, void *ctx __maybe_unused)
+static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused)
 {
 	return strcmp((const char *) key1, (const char *) key2) == 0;
 }
@@ -372,7 +372,7 @@ static int get_syms(char ***symsp, size_t *cntp)
 			     sizeof("__ftrace_invalid_address__") - 1))
 			continue;
 
-		err = hashmap__add(map, name, NULL);
+		err = hashmap__add(map, name, 0);
 		if (err == -EEXIST)
 			continue;
 		if (err)
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
index 617bbce6ef8f..5cf85d0f9827 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
@@ -485,7 +485,7 @@ static void misc(void)
 			goto check_linum;
 
 		ret = read(sk_fds.passive_fd, recv_msg, sizeof(recv_msg));
-		if (ASSERT_EQ(ret, sizeof(send_msg), "read(msg)"))
+		if (!ASSERT_EQ(ret, sizeof(send_msg), "read(msg)"))
 			goto check_linum;
 	}
 
@@ -505,6 +505,8 @@ static void misc(void)
 
 	ASSERT_EQ(misc_skel->bss->nr_fin, 1, "unexpected nr_fin");
 
+	ASSERT_EQ(misc_skel->bss->nr_hwtstamp, 0, "nr_hwtstamp");
+
 check_linum:
 	ASSERT_FALSE(check_error_linum(&sk_fds), "check_error_linum");
 	sk_fds_close(&sk_fds);
@@ -539,7 +541,7 @@ void test_tcp_hdr_options(void)
 		goto skel_destroy;
 
 	cg_fd = test__join_cgroup(CG_NAME);
-	if (ASSERT_GE(cg_fd, 0, "join_cgroup"))
+	if (!ASSERT_GE(cg_fd, 0, "join_cgroup"))
 		goto skel_destroy;
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
index 2c121c5d66a7..d487153a839d 100644
--- a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
@@ -27,6 +27,7 @@ unsigned int nr_pure_ack = 0;
 unsigned int nr_data = 0;
 unsigned int nr_syn = 0;
 unsigned int nr_fin = 0;
+unsigned int nr_hwtstamp = 0;
 
 /* Check the header received from the active side */
 static int __check_active_hdr_in(struct bpf_sock_ops *skops, bool check_syn)
@@ -146,6 +147,9 @@ static int check_active_hdr_in(struct bpf_sock_ops *skops)
 	if (th->ack && !th->fin && tcp_hdrlen(th) == skops->skb_len)
 		nr_pure_ack++;
 
+	if (skops->skb_hwtstamp)
+		nr_hwtstamp++;
+
 	return CG_OK;
 }
 
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 0e9a47f97890..c34f37d7a523 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -222,6 +222,26 @@ static char *test_result(bool failed, bool skipped)
 	return failed ? "FAIL" : (skipped ? "SKIP" : "OK");
 }
 
+#define TEST_NUM_WIDTH 7
+
+static void print_test_result(const struct prog_test_def *test, const struct test_state *test_state)
+{
+	int skipped_cnt = test_state->skip_cnt;
+	int subtests_cnt = test_state->subtest_num;
+
+	fprintf(env.stdout, "#%-*d %s:", TEST_NUM_WIDTH, test->test_num, test->test_name);
+	if (test_state->error_cnt)
+		fprintf(env.stdout, "FAIL");
+	else if (!skipped_cnt)
+		fprintf(env.stdout, "OK");
+	else if (skipped_cnt == subtests_cnt || !subtests_cnt)
+		fprintf(env.stdout, "SKIP");
+	else
+		fprintf(env.stdout, "OK (SKIP: %d/%d)", skipped_cnt, subtests_cnt);
+
+	fprintf(env.stdout, "\n");
+}
+
 static void print_test_log(char *log_buf, size_t log_cnt)
 {
 	log_buf[log_cnt] = '\0';
@@ -230,18 +250,6 @@ static void print_test_log(char *log_buf, size_t log_cnt)
 		fprintf(env.stdout, "\n");
 }
 
-#define TEST_NUM_WIDTH 7
-
-static void print_test_name(int test_num, const char *test_name, char *result)
-{
-	fprintf(env.stdout, "#%-*d %s", TEST_NUM_WIDTH, test_num, test_name);
-
-	if (result)
-		fprintf(env.stdout, ":%s", result);
-
-	fprintf(env.stdout, "\n");
-}
-
 static void print_subtest_name(int test_num, int subtest_num,
 			       const char *test_name, char *subtest_name,
 			       char *result)
@@ -307,8 +315,7 @@ static void dump_test_log(const struct prog_test_def *test,
 					       subtest_state->skipped));
 	}
 
-	print_test_name(test->test_num, test->test_name,
-			test_result(test_failed, test_state->skip_cnt));
+	print_test_result(test, test_state);
 }
 
 static void stdio_restore(void);
@@ -1070,8 +1077,7 @@ static void run_one_test(int test_num)
 	state->tested = true;
 
 	if (verbose() && env.worker_id == -1)
-		print_test_name(test_num + 1, test->test_name,
-				test_result(state->error_cnt, state->skip_cnt));
+		print_test_result(test, state);
 
 	reset_affinity();
 	restore_netns();
diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
index 973cbf6af323..f961b49b8ef4 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -17,6 +17,7 @@
 #include <bpf/libbpf.h>
 #include <libelf.h>
 #include <gelf.h>
+#include <float.h>
 
 enum stat_id {
 	VERDICT,
@@ -34,6 +35,45 @@ enum stat_id {
 	NUM_STATS_CNT = FILE_NAME - VERDICT,
 };
 
+/* In comparison mode each stat can specify up to four different values:
+ *   - A side value;
+ *   - B side value;
+ *   - absolute diff value;
+ *   - relative (percentage) diff value.
+ *
+ * When specifying stat specs in comparison mode, user can use one of the
+ * following variant suffixes to specify which exact variant should be used for
+ * ordering or filtering:
+ *   - `_a` for A side value;
+ *   - `_b` for B side value;
+ *   - `_diff` for absolute diff value;
+ *   - `_pct` for relative (percentage) diff value.
+ *
+ * If no variant suffix is provided, then `_b` (control data) is assumed.
+ *
+ * As an example, let's say instructions stat has the following output:
+ *
+ * Insns (A)  Insns (B)  Insns   (DIFF)
+ * ---------  ---------  --------------
+ * 21547      20920       -627 (-2.91%)
+ *
+ * Then:
+ *   - 21547 is A side value (insns_a);
+ *   - 20920 is B side value (insns_b);
+ *   - -627 is absolute diff value (insns_diff);
+ *   - -2.91% is relative diff value (insns_pct).
+ *
+ * For verdict there is no verdict_pct variant.
+ * For file and program name, _a and _b variants are equivalent and there are
+ * no _diff or _pct variants.
+ */
+enum stat_variant {
+	VARIANT_A,
+	VARIANT_B,
+	VARIANT_DIFF,
+	VARIANT_PCT,
+};
+
 struct verif_stats {
 	char *file_name;
 	char *prog_name;
@@ -41,9 +81,19 @@ struct verif_stats {
 	long stats[NUM_STATS_CNT];
 };
 
+/* joined comparison mode stats */
+struct verif_stats_join {
+	char *file_name;
+	char *prog_name;
+
+	const struct verif_stats *stats_a;
+	const struct verif_stats *stats_b;
+};
+
 struct stat_specs {
 	int spec_cnt;
 	enum stat_id ids[ALL_STATS_CNT];
+	enum stat_variant variants[ALL_STATS_CNT];
 	bool asc[ALL_STATS_CNT];
 	int lens[ALL_STATS_CNT * 3]; /* 3x for comparison mode */
 };
@@ -54,9 +104,31 @@ enum resfmt {
 	RESFMT_CSV,
 };
 
+enum filter_kind {
+	FILTER_NAME,
+	FILTER_STAT,
+};
+
+enum operator_kind {
+	OP_EQ,		/* == or = */
+	OP_NEQ,		/* != or <> */
+	OP_LT,		/* < */
+	OP_LE,		/* <= */
+	OP_GT,		/* > */
+	OP_GE,		/* >= */
+};
+
 struct filter {
+	enum filter_kind kind;
+	/* FILTER_NAME */
+	char *any_glob;
 	char *file_glob;
 	char *prog_glob;
+	/* FILTER_STAT */
+	enum operator_kind op;
+	int stat_id;
+	enum stat_variant stat_var;
+	long value;
 };
 
 static struct env {
@@ -67,6 +139,7 @@ static struct env {
 	int log_level;
 	enum resfmt out_fmt;
 	bool comparison_mode;
+	bool replay_mode;
 
 	struct verif_stats *prog_stats;
 	int prog_stat_cnt;
@@ -75,6 +148,9 @@ static struct env {
 	struct verif_stats *baseline_stats;
 	int baseline_stat_cnt;
 
+	struct verif_stats_join *join_stats;
+	int join_stat_cnt;
+
 	struct stat_specs output_spec;
 	struct stat_specs sort_spec;
 
@@ -115,6 +191,7 @@ static const struct argp_option opts[] = {
 	{ "sort", 's', "SPEC", 0, "Specify sort order" },
 	{ "output-format", 'o', "FMT", 0, "Result output format (table, csv), default is table." },
 	{ "compare", 'C', NULL, 0, "Comparison mode" },
+	{ "replay", 'R', NULL, 0, "Replay mode" },
 	{ "filter", 'f', "FILTER", 0, "Filter expressions (or @filename for file with expressions)." },
 	{},
 };
@@ -169,6 +246,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	case 'C':
 		env.comparison_mode = true;
 		break;
+	case 'R':
+		env.replay_mode = true;
+		break;
 	case 'f':
 		if (arg[0] == '@')
 			err = append_filter_file(arg + 1);
@@ -226,28 +306,6 @@ static bool glob_matches(const char *str, const char *pat)
 	return !*str && !*pat;
 }
 
-static bool should_process_file(const char *filename)
-{
-	int i;
-
-	if (env.deny_filter_cnt > 0) {
-		for (i = 0; i < env.deny_filter_cnt; i++) {
-			if (glob_matches(filename, env.deny_filters[i].file_glob))
-				return false;
-		}
-	}
-
-	if (env.allow_filter_cnt == 0)
-		return true;
-
-	for (i = 0; i < env.allow_filter_cnt; i++) {
-		if (glob_matches(filename, env.allow_filters[i].file_glob))
-			return true;
-	}
-
-	return false;
-}
-
 static bool is_bpf_obj_file(const char *path) {
 	Elf64_Ehdr *ehdr;
 	int fd, err = -EINVAL;
@@ -280,45 +338,84 @@ cleanup:
 	return err == 0;
 }
 
-static bool should_process_prog(const char *path, const char *prog_name)
+static bool should_process_file_prog(const char *filename, const char *prog_name)
 {
-	const char *filename = basename(path);
-	int i;
+	struct filter *f;
+	int i, allow_cnt = 0;
 
-	if (env.deny_filter_cnt > 0) {
-		for (i = 0; i < env.deny_filter_cnt; i++) {
-			if (glob_matches(filename, env.deny_filters[i].file_glob))
-				return false;
-			if (!env.deny_filters[i].prog_glob)
-				continue;
-			if (glob_matches(prog_name, env.deny_filters[i].prog_glob))
-				return false;
-		}
-	}
+	for (i = 0; i < env.deny_filter_cnt; i++) {
+		f = &env.deny_filters[i];
+		if (f->kind != FILTER_NAME)
+			continue;
 
-	if (env.allow_filter_cnt == 0)
-		return true;
+		if (f->any_glob && glob_matches(filename, f->any_glob))
+			return false;
+		if (f->any_glob && prog_name && glob_matches(prog_name, f->any_glob))
+			return false;
+		if (f->file_glob && glob_matches(filename, f->file_glob))
+			return false;
+		if (f->prog_glob && prog_name && glob_matches(prog_name, f->prog_glob))
+			return false;
+	}
 
 	for (i = 0; i < env.allow_filter_cnt; i++) {
-		if (!glob_matches(filename, env.allow_filters[i].file_glob))
+		f = &env.allow_filters[i];
+		if (f->kind != FILTER_NAME)
 			continue;
-		/* if filter specifies only filename glob part, it implicitly
-		 * allows all progs within that file
-		 */
-		if (!env.allow_filters[i].prog_glob)
-			return true;
-		if (glob_matches(prog_name, env.allow_filters[i].prog_glob))
+
+		allow_cnt++;
+		if (f->any_glob) {
+			if (glob_matches(filename, f->any_glob))
+				return true;
+			/* If we don't know program name yet, any_glob filter
+			 * has to assume that current BPF object file might be
+			 * relevant; we'll check again later on after opening
+			 * BPF object file, at which point program name will
+			 * be known finally.
+			 */
+			if (!prog_name || glob_matches(prog_name, f->any_glob))
+				return true;
+		} else {
+			if (f->file_glob && !glob_matches(filename, f->file_glob))
+				continue;
+			if (f->prog_glob && prog_name && !glob_matches(prog_name, f->prog_glob))
+				continue;
 			return true;
+		}
 	}
 
-	return false;
+	/* if there are no file/prog name allow filters, allow all progs,
+	 * unless they are denied earlier explicitly
+	 */
+	return allow_cnt == 0;
 }
 
+static struct {
+	enum operator_kind op_kind;
+	const char *op_str;
+} operators[] = {
+	/* Order of these definitions matter to avoid situations like '<'
+	 * matching part of what is actually a '<>' operator. That is,
+	 * substrings should go last.
+	 */
+	{ OP_EQ, "==" },
+	{ OP_NEQ, "!=" },
+	{ OP_NEQ, "<>" },
+	{ OP_LE, "<=" },
+	{ OP_LT, "<" },
+	{ OP_GE, ">=" },
+	{ OP_GT, ">" },
+	{ OP_EQ, "=" },
+};
+
+static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_variant *var);
+
 static int append_filter(struct filter **filters, int *cnt, const char *str)
 {
 	struct filter *f;
 	void *tmp;
 	const char *p;
+	int i;
 
 	tmp = realloc(*filters, (*cnt + 1) * sizeof(**filters));
 	if (!tmp)
@@ -326,26 +423,108 @@ static int append_filter(struct filter **filters, int *cnt, const char *str)
 	*filters = tmp;
 
 	f = &(*filters)[*cnt];
-	f->file_glob = f->prog_glob = NULL;
+	memset(f, 0, sizeof(*f));
+
+	/* First, let's check if it's a stats filter of the following form:
+	 * <stat><op><value, where:
+	 *   - <stat> is one of supported numerical stats (verdict is also
+	 *     considered numerical, failure == 0, success == 1);
+	 *   - <op> is comparison operator (see `operators` definitions);
+	 *   - <value> is an integer (or failure/success, or false/true as
+	 *     special aliases for 0 and 1, respectively).
+	 * If the form doesn't match what user provided, we assume file/prog
+	 * glob filter.
+	 */
+	for (i = 0; i < ARRAY_SIZE(operators); i++) {
+		enum stat_variant var;
+		int id;
+		long val;
+		const char *end = str;
+		const char *op_str;
 
-	/* filter can be specified either as "<obj-glob>" or "<obj-glob>/<prog-glob>" */
+		op_str = operators[i].op_str;
+		p = strstr(str, op_str);
+		if (!p)
+			continue;
+
+		if (!parse_stat_id_var(str, p - str, &id, &var)) {
+			fprintf(stderr, "Unrecognized stat name in '%s'!\n", str);
+			return -EINVAL;
+		}
+		if (id >= FILE_NAME) {
+			fprintf(stderr, "Non-integer stat is specified in '%s'!\n", str);
+			return -EINVAL;
+		}
+
+		p += strlen(op_str);
+
+		if (strcasecmp(p, "true") == 0 ||
+		    strcasecmp(p, "t") == 0 ||
+		    strcasecmp(p, "success") == 0 ||
+		    strcasecmp(p, "succ") == 0 ||
+		    strcasecmp(p, "s") == 0 ||
+		    strcasecmp(p, "match") == 0 ||
+		    strcasecmp(p, "m") == 0) {
+			val = 1;
+		} else if (strcasecmp(p, "false") == 0 ||
+			   strcasecmp(p, "f") == 0 ||
+			   strcasecmp(p, "failure") == 0 ||
+			   strcasecmp(p, "fail") == 0 ||
+			   strcasecmp(p, "mismatch") == 0 ||
+			   strcasecmp(p, "mis") == 0) {
+			val = 0;
+		} else {
+			errno = 0;
+			val = strtol(p, (char **)&end, 10);
+			if (errno || end == p || *end != '\0' ) {
+				fprintf(stderr, "Invalid integer value in '%s'!\n", str);
+				return -EINVAL;
+			}
+		}
+
+		f->kind = FILTER_STAT;
+		f->stat_id = id;
+		f->stat_var = var;
+		f->op = operators[i].op_kind;
+		f->value = val;
+
+		*cnt += 1;
+		return 0;
+	}
+
+	/* File/prog filter can be specified either as '<glob>' or
+	 * '<file-glob>/<prog-glob>'. In the former case <glob> is applied to
+	 * both file and program names. This seems to be way more useful in
+	 * practice. If user needs full control, they can use '/<prog-glob>'
+	 * form to glob just program name, or '<file-glob>/' to glob only file
+	 * name. But usually common <glob> seems to be the most useful and
+	 * ergonomic way.
+	 */
+	f->kind = FILTER_NAME;
 	p = strchr(str, '/');
 	if (!p) {
-		f->file_glob = strdup(str);
-		if (!f->file_glob)
+		f->any_glob = strdup(str);
+		if (!f->any_glob)
 			return -ENOMEM;
 	} else {
-		f->file_glob = strndup(str, p - str);
-		f->prog_glob = strdup(p + 1);
-		if (!f->file_glob || !f->prog_glob) {
-			free(f->file_glob);
-			free(f->prog_glob);
-			f->file_glob = f->prog_glob = NULL;
-			return -ENOMEM;
+		if (str != p) {
+			/* non-empty file glob */
+			f->file_glob = strndup(str, p - str);
+			if (!f->file_glob)
+				return -ENOMEM;
+		}
+		if (strlen(p + 1) > 0) {
+			/* non-empty prog glob */
+			f->prog_glob = strdup(p + 1);
+			if (!f->prog_glob) {
+				free(f->file_glob);
+				f->file_glob = NULL;
+				return -ENOMEM;
+			}
 		}
 	}
 
-	*cnt = *cnt + 1;
+	*cnt += 1;
 	return 0;
 }
 
@@ -388,6 +567,15 @@ static const struct stat_specs default_output_spec = {
 	},
 };
 
+static const struct stat_specs default_csv_output_spec = {
+	.spec_cnt = 9,
+	.ids = {
+		FILE_NAME, PROG_NAME, VERDICT, DURATION,
+		TOTAL_INSNS, TOTAL_STATES, PEAK_STATES,
+		MAX_STATES_PER_INSN, MARK_READ_MAX_LEN,
+	},
+};
+
 static const struct stat_specs default_sort_spec = {
 	.spec_cnt = 2,
 	.ids = {
@@ -396,48 +584,123 @@ static const struct stat_specs default_sort_spec = {
 	.asc = { true, true, },
 };
 
+/* sorting for comparison mode to join two data sets */
+static const struct stat_specs join_sort_spec = {
+	.spec_cnt = 2,
+	.ids = {
+		FILE_NAME, PROG_NAME,
+	},
+	.asc = { true, true, },
+};
+
 static struct stat_def {
 	const char *header;
 	const char *names[4];
 	bool asc_by_default;
+	bool left_aligned;
 } stat_defs[] = {
-	[FILE_NAME] = { "File", {"file_name", "filename", "file"}, true /* asc */ },
-	[PROG_NAME] = { "Program", {"prog_name", "progname", "prog"}, true /* asc */ },
-	[VERDICT] = { "Verdict", {"verdict"}, true /* asc: failure, success */ },
+	[FILE_NAME] = { "File", {"file_name", "filename", "file"}, true /* asc */, true /* left */ },
+	[PROG_NAME] = { "Program", {"prog_name", "progname", "prog"}, true /* asc */, true /* left */ },
+	[VERDICT] = { "Verdict", {"verdict"}, true /* asc: failure, success */, true /* left */ },
 	[DURATION] = { "Duration (us)", {"duration", "dur"}, },
-	[TOTAL_INSNS] = { "Total insns", {"total_insns", "insns"}, },
-	[TOTAL_STATES] = { "Total states", {"total_states", "states"}, },
+	[TOTAL_INSNS] = { "Insns", {"total_insns", "insns"}, },
+	[TOTAL_STATES] = { "States", {"total_states", "states"}, },
 	[PEAK_STATES] = { "Peak states", {"peak_states"}, },
 	[MAX_STATES_PER_INSN] = { "Max states per insn", {"max_states_per_insn"}, },
 	[MARK_READ_MAX_LEN] = { "Max mark read length", {"max_mark_read_len", "mark_read"}, },
 };
 
+static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_variant *var)
+{
+	static const char *var_sfxs[] = {
+		[VARIANT_A] = "_a",
+		[VARIANT_B] = "_b",
+		[VARIANT_DIFF] = "_diff",
+		[VARIANT_PCT] = "_pct",
+	};
+	int i, j, k;
+
+	for (i = 0; i < ARRAY_SIZE(stat_defs); i++) {
+		struct stat_def *def = &stat_defs[i];
+		size_t alias_len, sfx_len;
+		const char *alias;
+
+		for (j = 0; j < ARRAY_SIZE(stat_defs[i].names); j++) {
+			alias = def->names[j];
+			if (!alias)
+				continue;
+
+			alias_len = strlen(alias);
+			if (strncmp(name, alias, alias_len) != 0)
+				continue;
+
+			if (alias_len == len) {
+				/* If no variant suffix is specified, we
+				 * assume control group (just in case we are
+				 * in comparison mode. Variant is ignored in
+				 * non-comparison mode.
+				 */
+				*var = VARIANT_B;
+				*id = i;
+				return true;
+			}
+
+			for (k = 0; k < ARRAY_SIZE(var_sfxs); k++) {
+				sfx_len = strlen(var_sfxs[k]);
+				if (alias_len + sfx_len != len)
+					continue;
+
+				if (strncmp(name + alias_len, var_sfxs[k], sfx_len) == 0) {
+					*var = (enum stat_variant)k;
+					*id = i;
+					return true;
+				}
+			}
+		}
+	}
+
+	return false;
+}
+
+static bool is_asc_sym(char c)
+{
+	return c == '^';
+}
+
+static bool is_desc_sym(char c)
+{
+	return c == 'v' || c == 'V' || c == '.' || c == '!' || c == '_';
+}
+
 static int parse_stat(const char *stat_name, struct stat_specs *specs)
 {
-	int id, i;
+	int id;
+	bool has_order = false, is_asc = false;
+	size_t len = strlen(stat_name);
+	enum stat_variant var;
 
 	if (specs->spec_cnt >= ARRAY_SIZE(specs->ids)) {
 		fprintf(stderr, "Can't specify more than %zd stats\n", ARRAY_SIZE(specs->ids));
 		return -E2BIG;
 	}
 
-	for (id = 0; id < ARRAY_SIZE(stat_defs); id++) {
-		struct stat_def *def = &stat_defs[id];
-
-		for (i = 0; i < ARRAY_SIZE(stat_defs[id].names); i++) {
-			if (!def->names[i] || strcmp(def->names[i], stat_name) != 0)
-				continue;
-
-			specs->ids[specs->spec_cnt] = id;
-			specs->asc[specs->spec_cnt] = def->asc_by_default;
-			specs->spec_cnt++;
+	if (len > 1 && (is_asc_sym(stat_name[len - 1]) || is_desc_sym(stat_name[len - 1]))) {
+		has_order = true;
+		is_asc = is_asc_sym(stat_name[len - 1]);
+		len -= 1;
+	}
 
-			return 0;
-		}
+	if (!parse_stat_id_var(stat_name, len, &id, &var)) {
+		fprintf(stderr, "Unrecognized stat name '%s'\n", stat_name);
+		return -ESRCH;
 	}
 
-	fprintf(stderr, "Unrecognized stat name '%s'\n", stat_name);
-	return -ESRCH;
+	specs->ids[specs->spec_cnt] = id;
+	specs->variants[specs->spec_cnt] = var;
+	specs->asc[specs->spec_cnt] = has_order ? is_asc : stat_defs[id].asc_by_default;
+	specs->spec_cnt++;
+
+	return 0;
 }
 
 static int parse_stats(const char *stats_str, struct stat_specs *specs)
@@ -540,7 +803,7 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
 	int err = 0;
 	void *tmp;
 
-	if (!should_process_prog(filename, bpf_program__name(prog))) {
+	if (!should_process_file_prog(basename(filename), bpf_program__name(prog))) {
 		env.progs_skipped++;
 		return 0;
 	}
@@ -596,7 +859,7 @@ static int process_obj(const char *filename)
 	LIBBPF_OPTS(bpf_object_open_opts, opts);
 	int err = 0, prog_cnt = 0;
 
-	if (!should_process_file(basename(filename))) {
+	if (!should_process_file_prog(basename(filename), NULL)) {
 		if (env.verbose)
 			printf("Skipping '%s' due to filters...\n", filename);
 		env.files_skipped++;
@@ -716,7 +979,106 @@ static int cmp_prog_stats(const void *v1, const void *v2)
 			return cmp;
 	}
 
-	return 0;
+	/* always disambiguate with file+prog, which are unique */
+	cmp = strcmp(s1->file_name, s2->file_name);
+	if (cmp != 0)
+		return cmp;
+	return strcmp(s1->prog_name, s2->prog_name);
+}
+
+static void fetch_join_stat_value(const struct verif_stats_join *s,
+				  enum stat_id id, enum stat_variant var,
+				  const char **str_val,
+				  double *num_val)
+{
+	long v1, v2;
+
+	if (id == FILE_NAME) {
+		*str_val = s->file_name;
+		return;
+	}
+	if (id == PROG_NAME) {
+		*str_val = s->prog_name;
+		return;
+	}
+
+	v1 = s->stats_a ? s->stats_a->stats[id] : 0;
+	v2 = s->stats_b ? s->stats_b->stats[id] : 0;
+
+	switch (var) {
+	case VARIANT_A:
+		if (!s->stats_a)
+			*num_val = -DBL_MAX;
+		else
+			*num_val = s->stats_a->stats[id];
+		return;
+	case VARIANT_B:
+		if (!s->stats_b)
+			*num_val = -DBL_MAX;
+		else
+			*num_val = s->stats_b->stats[id];
+		return;
+	case VARIANT_DIFF:
+		if (!s->stats_a || !s->stats_b)
+			*num_val = -DBL_MAX;
+		else if (id == VERDICT)
+			*num_val = v1 == v2 ? 1.0 /* MATCH */ : 0.0 /* MISMATCH */;
+		else
+			*num_val = (double)(v2 - v1);
+		return;
+	case VARIANT_PCT:
+		if (!s->stats_a || !s->stats_b) {
+			*num_val = -DBL_MAX;
+		} else if (v1 == 0) {
+			if (v1 == v2)
+				*num_val = 0.0;
+			else
+				*num_val = v2 < v1 ? -100.0 : 100.0;
+		} else {
+			 *num_val = (v2 - v1) * 100.0 / v1;
+		}
+		return;
+	}
+}
+
+static int cmp_join_stat(const struct verif_stats_join *s1,
+			 const struct verif_stats_join *s2,
+			 enum stat_id id, enum stat_variant var, bool asc)
+{
+	const char *str1 = NULL, *str2 = NULL;
+	double v1, v2;
+	int cmp = 0;
+
+	fetch_join_stat_value(s1, id, var, &str1, &v1);
+	fetch_join_stat_value(s2, id, var, &str2, &v2);
+
+	if (str1)
+		cmp = strcmp(str1, str2);
+	else if (v1 != v2)
+		cmp = v1 < v2 ? -1 : 1;
+
+	return asc ? cmp : -cmp;
+}
+
+static int cmp_join_stats(const void *v1, const void *v2)
+{
+	const struct verif_stats_join *s1 = v1, *s2 = v2;
+	int i, cmp;
+
+	for (i = 0; i < env.sort_spec.spec_cnt; i++) {
+		cmp = cmp_join_stat(s1, s2,
+				    env.sort_spec.ids[i],
+				    env.sort_spec.variants[i],
+				    env.sort_spec.asc[i]);
+		if (cmp != 0)
+			return cmp;
+	}
+
+	/* always disambiguate with file+prog, which are unique */
+	cmp = strcmp(s1->file_name, s2->file_name);
+	if (cmp != 0)
+		return cmp;
+	return strcmp(s1->prog_name, s2->prog_name);
 }
 
 #define HEADER_CHAR '-'
@@ -738,6 +1100,7 @@ static void output_header_underlines(void)
 
 static void output_headers(enum resfmt fmt)
 {
+	const char *fmt_str;
 	int i, len;
 
 	for (i = 0; i < env.output_spec.spec_cnt; i++) {
@@ -751,7 +1114,8 @@ static void output_headers(enum resfmt fmt)
 				*max_len = len;
 			break;
 		case RESFMT_TABLE:
-			printf("%s%-*s", i == 0 ? "" : COLUMN_SEP,  *max_len, stat_defs[id].header);
+			fmt_str = stat_defs[id].left_aligned ? "%s%-*s" : "%s%*s";
+			printf(fmt_str, i == 0 ? "" : COLUMN_SEP,  *max_len, stat_defs[id].header);
 			if (i == env.output_spec.spec_cnt - 1)
 				printf("\n");
 			break;
@@ -772,13 +1136,16 @@ static void prepare_value(const struct verif_stats *s, enum stat_id id,
 {
 	switch (id) {
 	case FILE_NAME:
-		*str = s->file_name;
+		*str = s ? s->file_name : "N/A";
 		break;
 	case PROG_NAME:
-		*str = s->prog_name;
+		*str = s ? s->prog_name : "N/A";
 		break;
 	case VERDICT:
-		*str = s->stats[VERDICT] ? "success" : "failure";
+		if (!s)
+			*str = "N/A";
+		else
+			*str = s->stats[VERDICT] ? "success" : "failure";
 		break;
 	case DURATION:
 	case TOTAL_INSNS:
@@ -786,7 +1153,7 @@ static void prepare_value(const struct verif_stats *s, enum stat_id id,
 	case PEAK_STATES:
 	case MAX_STATES_PER_INSN:
 	case MARK_READ_MAX_LEN:
-		*val = s->stats[id];
+		*val = s ? s->stats[id] : 0;
 		break;
 	default:
 		fprintf(stderr, "Unrecognized stat #%d\n", id);
@@ -841,42 +1208,6 @@ static void output_stats(const struct verif_stats *s, enum resfmt fmt, bool last
 	}
 }
 
-static int handle_verif_mode(void)
-{
-	int i, err;
-
-	if (env.filename_cnt == 0) {
-		fprintf(stderr, "Please provide path to BPF object file!\n");
-		argp_help(&argp, stderr, ARGP_HELP_USAGE, "veristat");
-		return -EINVAL;
-	}
-
-	for (i = 0; i < env.filename_cnt; i++) {
-		err = process_obj(env.filenames[i]);
-		if (err) {
-			fprintf(stderr, "Failed to process '%s': %d\n", env.filenames[i], err);
-			return err;
-		}
-	}
-
-	qsort(env.prog_stats, env.prog_stat_cnt, sizeof(*env.prog_stats), cmp_prog_stats);
-
-	if (env.out_fmt == RESFMT_TABLE) {
-		/* calculate column widths */
-		output_headers(RESFMT_TABLE_CALCLEN);
-		for (i = 0; i < env.prog_stat_cnt; i++)
-			output_stats(&env.prog_stats[i], RESFMT_TABLE_CALCLEN, false);
-	}
-
-	/* actually output the table */
-	output_headers(env.out_fmt);
-	for (i = 0; i < env.prog_stat_cnt; i++) {
-		output_stats(&env.prog_stats[i], env.out_fmt, i == env.prog_stat_cnt - 1);
-	}
-
-	return 0;
-}
-
 static int parse_stat_value(const char *str, enum stat_id id, struct verif_stats *st)
 {
 	switch (id) {
@@ -1008,7 +1339,7 @@ static int parse_stats_csv(const char *filename, struct stat_specs *specs,
 		 * parsed entire line; if row should be ignored we pretend we
 		 * never parsed it
 		 */
-		if (!should_process_prog(st->file_name, st->prog_name)) {
+		if (!should_process_file_prog(st->file_name, st->prog_name)) {
 			free(st->file_name);
 			free(st->prog_name);
 			*stat_cntp -= 1;
@@ -1097,9 +1428,11 @@ static void output_comp_headers(enum resfmt fmt)
 		output_comp_header_underlines();
 }
 
-static void output_comp_stats(const struct verif_stats *base, const struct verif_stats *comp,
+static void output_comp_stats(const struct verif_stats_join *join_stats,
 			      enum resfmt fmt, bool last)
 {
+	const struct verif_stats *base = join_stats->stats_a;
+	const struct verif_stats *comp = join_stats->stats_b;
 	char base_buf[1024] = {}, comp_buf[1024] = {}, diff_buf[1024] = {};
 	int i;
 
@@ -1117,33 +1450,45 @@ static void output_comp_stats(const struct verif_stats *base, const struct verif
 		/* normalize all the outputs to be in string buffers for simplicity */
 		if (is_key_stat(id)) {
 			/* key stats (file and program name) are always strings */
-			if (base != &fallback_stats)
+			if (base)
 				snprintf(base_buf, sizeof(base_buf), "%s", base_str);
 			else
 				snprintf(base_buf, sizeof(base_buf), "%s", comp_str);
 		} else if (base_str) {
 			snprintf(base_buf, sizeof(base_buf), "%s", base_str);
 			snprintf(comp_buf, sizeof(comp_buf), "%s", comp_str);
-			if (strcmp(base_str, comp_str) == 0)
+			if (!base || !comp)
+				snprintf(diff_buf, sizeof(diff_buf), "%s", "N/A");
+			else if (strcmp(base_str, comp_str) == 0)
 				snprintf(diff_buf, sizeof(diff_buf), "%s", "MATCH");
 			else
 				snprintf(diff_buf, sizeof(diff_buf), "%s", "MISMATCH");
 		} else {
 			double p = 0.0;
 
-			snprintf(base_buf, sizeof(base_buf), "%ld", base_val);
-			snprintf(comp_buf, sizeof(comp_buf), "%ld", comp_val);
+			if (base)
+				snprintf(base_buf, sizeof(base_buf), "%ld", base_val);
+			else
+				snprintf(base_buf, sizeof(base_buf), "%s", "N/A");
+			if (comp)
+				snprintf(comp_buf, sizeof(comp_buf), "%ld", comp_val);
+			else
+				snprintf(comp_buf, sizeof(comp_buf), "%s", "N/A");
 
 			diff_val = comp_val - base_val;
-			if (base == &fallback_stats || comp == &fallback_stats || base_val == 0) {
-				if (comp_val == base_val)
-					p = 0.0; /* avoid +0 (+100%) case */
-				else
-					p = comp_val < base_val ? -100.0 : 100.0;
+			if (!base || !comp) {
+				snprintf(diff_buf, sizeof(diff_buf), "%s", "N/A");
 			} else {
-				 p = diff_val * 100.0 / base_val;
+				if (base_val == 0) {
+					if (comp_val == base_val)
+						p = 0.0; /* avoid +0 (+100%) case */
+					else
+						p = comp_val < base_val ? -100.0 : 100.0;
+				} else {
+					 p = diff_val * 100.0 / base_val;
+				}
+				snprintf(diff_buf, sizeof(diff_buf), "%+ld (%+.2lf%%)", diff_val, p);
 			}
-			snprintf(diff_buf, sizeof(diff_buf), "%+ld (%+.2lf%%)", diff_val, p);
 		}
 
 		switch (fmt) {
@@ -1199,14 +1544,64 @@ static int cmp_stats_key(const struct verif_stats *base, const struct verif_stat
 	return strcmp(base->prog_name, comp->prog_name);
 }
 
+static bool is_join_stat_filter_matched(struct filter *f, const struct verif_stats_join *stats)
+{
+	static const double eps = 1e-9;
+	const char *str = NULL;
+	double value = 0.0;
+
+	fetch_join_stat_value(stats, f->stat_id, f->stat_var, &str, &value);
+
+	switch (f->op) {
+	case OP_EQ: return value > f->value - eps && value < f->value + eps;
+	case OP_NEQ: return value < f->value - eps || value > f->value + eps;
+	case OP_LT: return value < f->value - eps;
+	case OP_LE: return value <= f->value + eps;
+	case OP_GT: return value > f->value + eps;
+	case OP_GE: return value >= f->value - eps;
+	}
+
+	fprintf(stderr, "BUG: unknown filter op %d!\n", f->op);
+	return false;
+}
+
+static bool should_output_join_stats(const struct verif_stats_join *stats)
+{
+	struct filter *f;
+	int i, allow_cnt = 0;
+
+	for (i = 0; i < env.deny_filter_cnt; i++) {
+		f = &env.deny_filters[i];
+		if (f->kind != FILTER_STAT)
+			continue;
+
+		if (is_join_stat_filter_matched(f, stats))
+			return false;
+	}
+
+	for (i = 0; i < env.allow_filter_cnt; i++) {
+		f = &env.allow_filters[i];
+		if (f->kind != FILTER_STAT)
+			continue;
+		allow_cnt++;
+
+		if (is_join_stat_filter_matched(f, stats))
+			return true;
+	}
+
+	/* if there are no stat allowed filters, pass everything through */
+	return allow_cnt == 0;
+}
+
 static int handle_comparison_mode(void)
 {
 	struct stat_specs base_specs = {}, comp_specs = {};
+	struct stat_specs tmp_sort_spec;
 	enum resfmt cur_fmt;
-	int err, i, j;
+	int err, i, j, last_idx;
 
 	if (env.filename_cnt != 2) {
-		fprintf(stderr, "Comparison mode expects exactly two input CSV files!\n");
+		fprintf(stderr, "Comparison mode expects exactly two input CSV files!\n\n");
 		argp_help(&argp, stderr, ARGP_HELP_USAGE, "veristat");
 		return -EINVAL;
 	}
@@ -1244,31 +1639,26 @@ static int handle_comparison_mode(void)
 		}
 	}
 
+	/* Replace user-specified sorting spec with file+prog sorting rule to
+	 * be able to join two datasets correctly. Once we are done, we will
+	 * restore the original sort spec.
+	 */
+	tmp_sort_spec = env.sort_spec;
+	env.sort_spec = join_sort_spec;
 	qsort(env.prog_stats, env.prog_stat_cnt, sizeof(*env.prog_stats), cmp_prog_stats);
 	qsort(env.baseline_stats, env.baseline_stat_cnt, sizeof(*env.baseline_stats), cmp_prog_stats);
+	env.sort_spec = tmp_sort_spec;
 
-	/* for human-readable table output we need to do extra pass to
-	 * calculate column widths, so we substitute current output format
-	 * with RESFMT_TABLE_CALCLEN and later revert it back to RESFMT_TABLE
-	 * and do everything again.
-	 */
-	if (env.out_fmt == RESFMT_TABLE)
-		cur_fmt = RESFMT_TABLE_CALCLEN;
-	else
-		cur_fmt = env.out_fmt;
-
-one_more_time:
-	output_comp_headers(cur_fmt);
-
-	/* If baseline and comparison datasets have different subset of rows
-	 * (we match by 'object + prog' as a unique key) then assume
-	 * empty/missing/zero value for rows that are missing in the opposite
-	 * data set
+	/* Join two datasets together. If baseline and comparison datasets
+	 * have different subset of rows (we match by 'object + prog' as
+	 * a unique key) then assume empty/missing/zero value for rows that
+	 * are missing in the opposite data set.
 	 */
 	i = j = 0;
 	while (i < env.baseline_stat_cnt || j < env.prog_stat_cnt) {
-		bool last = (i == env.baseline_stat_cnt - 1) || (j == env.prog_stat_cnt - 1);
 		const struct verif_stats *base, *comp;
+		struct verif_stats_join *join;
+		void *tmp;
 		int r;
 
 		base = i < env.baseline_stat_cnt ? &env.baseline_stats[i] : &fallback_stats;
@@ -1285,18 +1675,64 @@ one_more_time:
 			return -EINVAL;
 		}
 
+		tmp = realloc(env.join_stats, (env.join_stat_cnt + 1) * sizeof(*env.join_stats));
+		if (!tmp)
+			return -ENOMEM;
+		env.join_stats = tmp;
+
+		join = &env.join_stats[env.join_stat_cnt];
+		memset(join, 0, sizeof(*join));
+
 		r = cmp_stats_key(base, comp);
 		if (r == 0) {
-			output_comp_stats(base, comp, cur_fmt, last);
+			join->file_name = base->file_name;
+			join->prog_name = base->prog_name;
+			join->stats_a = base;
+			join->stats_b = comp;
 			i++;
 			j++;
 		} else if (comp == &fallback_stats || r < 0) {
-			output_comp_stats(base, &fallback_stats, cur_fmt, last);
+			join->file_name = base->file_name;
+			join->prog_name = base->prog_name;
+			join->stats_a = base;
+			join->stats_b = NULL;
 			i++;
 		} else {
-			output_comp_stats(&fallback_stats, comp, cur_fmt, last);
+			join->file_name = comp->file_name;
+			join->prog_name = comp->prog_name;
+			join->stats_a = NULL;
+			join->stats_b = comp;
 			j++;
 		}
+		env.join_stat_cnt += 1;
+	}
+
+	/* now sort joined results accorsing to sort spec */
+	qsort(env.join_stats, env.join_stat_cnt, sizeof(*env.join_stats), cmp_join_stats);
+
+	/* for human-readable table output we need to do extra pass to
+	 * calculate column widths, so we substitute current output format
+	 * with RESFMT_TABLE_CALCLEN and later revert it back to RESFMT_TABLE
+	 * and do everything again.
+	 */
+	if (env.out_fmt == RESFMT_TABLE)
+		cur_fmt = RESFMT_TABLE_CALCLEN;
+	else
+		cur_fmt = env.out_fmt;
+
+one_more_time:
+	output_comp_headers(cur_fmt);
+
+	for (i = 0; i < env.join_stat_cnt; i++) {
+		const struct verif_stats_join *join = &env.join_stats[i];
+
+		if (!should_output_join_stats(join))
+			continue;
+
+		if (cur_fmt == RESFMT_TABLE_CALCLEN)
+			last_idx = i;
+
+		output_comp_stats(join, cur_fmt, i == last_idx);
 	}
 
 	if (cur_fmt == RESFMT_TABLE_CALCLEN) {
@@ -1307,6 +1743,128 @@ one_more_time:
 	return 0;
 }
 
+static bool is_stat_filter_matched(struct filter *f, const struct verif_stats *stats)
+{
+	long value = stats->stats[f->stat_id];
+
+	switch (f->op) {
+	case OP_EQ: return value == f->value;
+	case OP_NEQ: return value != f->value;
+	case OP_LT: return value < f->value;
+	case OP_LE: return value <= f->value;
+	case OP_GT: return value > f->value;
+	case OP_GE: return value >= f->value;
+	}
+
+	fprintf(stderr, "BUG: unknown filter op %d!\n", f->op);
+	return false;
+}
+
+static bool should_output_stats(const struct verif_stats *stats)
+{
+	struct filter *f;
+	int i, allow_cnt = 0;
+
+	for (i = 0; i < env.deny_filter_cnt; i++) {
+		f = &env.deny_filters[i];
+		if (f->kind != FILTER_STAT)
+			continue;
+
+		if (is_stat_filter_matched(f, stats))
+			return false;
+	}
+
+	for (i = 0; i < env.allow_filter_cnt; i++) {
+		f = &env.allow_filters[i];
+		if (f->kind != FILTER_STAT)
+			continue;
+		allow_cnt++;
+
+		if (is_stat_filter_matched(f, stats))
+			return true;
+	}
+
+	/* if there are no stat allowed filters, pass everything through */
+	return allow_cnt == 0;
+}
+
+static void output_prog_stats(void)
+{
+	const struct verif_stats *stats;
+	int i, last_stat_idx = 0;
+
+	if (env.out_fmt == RESFMT_TABLE) {
+		/* calculate column widths */
+		output_headers(RESFMT_TABLE_CALCLEN);
+		for (i = 0; i < env.prog_stat_cnt; i++) {
+			stats = &env.prog_stats[i];
+			if (!should_output_stats(stats))
+				continue;
+			output_stats(stats, RESFMT_TABLE_CALCLEN, false);
+			last_stat_idx = i;
+		}
+	}
+
+	/* actually output the table */
+	output_headers(env.out_fmt);
+	for (i = 0; i < env.prog_stat_cnt; i++) {
+		stats = &env.prog_stats[i];
+		if (!should_output_stats(stats))
+			continue;
+		output_stats(stats, env.out_fmt, i == last_stat_idx);
+	}
+}
+
+static int handle_verif_mode(void)
+{
+	int i, err;
+
+	if (env.filename_cnt == 0) {
+		fprintf(stderr, "Please provide path to BPF object file!\n\n");
+		argp_help(&argp, stderr, ARGP_HELP_USAGE, "veristat");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < env.filename_cnt; i++) {
+		err = process_obj(env.filenames[i]);
+		if (err) {
+			fprintf(stderr, "Failed to process '%s': %d\n", env.filenames[i], err);
+			return err;
+		}
+	}
+
+	qsort(env.prog_stats, env.prog_stat_cnt, sizeof(*env.prog_stats), cmp_prog_stats);
+
+	output_prog_stats();
+
+	return 0;
+}
+
+static int handle_replay_mode(void)
+{
+	struct stat_specs specs = {};
+	int err;
+
+	if (env.filename_cnt != 1) {
+		fprintf(stderr, "Replay mode expects exactly one input CSV file!\n\n");
+		argp_help(&argp, stderr, ARGP_HELP_USAGE, "veristat");
+		return -EINVAL;
+	}
+
+	err = parse_stats_csv(env.filenames[0], &specs,
+			      &env.prog_stats, &env.prog_stat_cnt);
+	if (err) {
+		fprintf(stderr, "Failed to parse stats from '%s': %d\n", env.filenames[0], err);
+		return err;
+	}
+
+	qsort(env.prog_stats, env.prog_stat_cnt, sizeof(*env.prog_stats), cmp_prog_stats);
+
+	output_prog_stats();
+
+	return 0;
+}
+
 int main(int argc, char **argv)
 {
 	int err = 0, i;
@@ -1315,34 +1873,49 @@ int main(int argc, char **argv)
 		return 1;
 
 	if (env.verbose && env.quiet) {
-		fprintf(stderr, "Verbose and quiet modes are incompatible, please specify just one or neither!\n");
+		fprintf(stderr, "Verbose and quiet modes are incompatible, please specify just one or neither!\n\n");
 		argp_help(&argp, stderr, ARGP_HELP_USAGE, "veristat");
 		return 1;
 	}
 	if (env.verbose && env.log_level == 0)
 		env.log_level = 1;
 
-	if (env.output_spec.spec_cnt == 0)
-		env.output_spec = default_output_spec;
+	if (env.output_spec.spec_cnt == 0) {
+		if (env.out_fmt == RESFMT_CSV)
+			env.output_spec = default_csv_output_spec;
+		else
+			env.output_spec = default_output_spec;
+	}
 	if (env.sort_spec.spec_cnt == 0)
 		env.sort_spec = default_sort_spec;
 
+	if (env.comparison_mode && env.replay_mode) {
+		fprintf(stderr, "Can't specify replay and comparison mode at the same time!\n\n");
+		argp_help(&argp, stderr, ARGP_HELP_USAGE, "veristat");
+		return 1;
+	}
+
 	if (env.comparison_mode)
 		err = handle_comparison_mode();
+	else if (env.replay_mode)
+		err = handle_replay_mode();
 	else
 		err = handle_verif_mode();
 
 	free_verif_stats(env.prog_stats, env.prog_stat_cnt);
 	free_verif_stats(env.baseline_stats, env.baseline_stat_cnt);
+	free(env.join_stats);
 	for (i = 0; i < env.filename_cnt; i++)
 		free(env.filenames[i]);
 	free(env.filenames);
 	for (i = 0; i < env.allow_filter_cnt; i++) {
+		free(env.allow_filters[i].any_glob);
 		free(env.allow_filters[i].file_glob);
 		free(env.allow_filters[i].prog_glob);
 	}
 	free(env.allow_filters);
 	for (i = 0; i < env.deny_filter_cnt; i++) {
+		free(env.deny_filters[i].any_glob);
 		free(env.deny_filters[i].file_glob);
 		free(env.deny_filters[i].prog_glob);
 	}
diff --git a/tools/testing/selftests/bpf/xdp_synproxy.c b/tools/testing/selftests/bpf/xdp_synproxy.c
index ff35320d2be9..410a1385a01d 100644
--- a/tools/testing/selftests/bpf/xdp_synproxy.c
+++ b/tools/testing/selftests/bpf/xdp_synproxy.c
@@ -104,7 +104,8 @@ static void parse_options(int argc, char *argv[], unsigned int *ifindex, __u32 *
 		{ "tc", no_argument, NULL, 'c' },
 		{ NULL, 0, NULL, 0 },
 	};
-	unsigned long mss4, mss6, wscale, ttl;
+	unsigned long mss4, wscale, ttl;
+	unsigned long long mss6;
 	unsigned int tcpipopts_mask = 0;
 
 	if (argc < 2)
@@ -286,7 +287,7 @@ static int syncookie_open_bpf_maps(__u32 prog_id, int *values_map_fd, int *ports
 
 	prog_info = (struct bpf_prog_info) {
 		.nr_map_ids = 8,
-		.map_ids = (__u64)map_ids,
+		.map_ids = (__u64)(unsigned long)map_ids,
 	};
 	info_len = sizeof(prog_info);
 
diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c
index 0b3ff49c740d..39d349509ba4 100644
--- a/tools/testing/selftests/bpf/xsk.c
+++ b/tools/testing/selftests/bpf/xsk.c
@@ -33,6 +33,7 @@
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
 #include "xsk.h"
+#include "bpf_util.h"
 
 #ifndef SOL_XDP
  #define SOL_XDP 283
@@ -521,25 +522,6 @@ static int xsk_create_bpf_link(struct xsk_socket *xsk)
 	return 0;
 }
 
-/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst
- * is zero-terminated string no matter what (unless sz == 0, in which case
- * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs
- * in what is returned. Given this is internal helper, it's trivial to extend
- * this, when necessary. Use this instead of strncpy inside libbpf source code.
- */
-static inline void libbpf_strlcpy(char *dst, const char *src, size_t sz)
-{
-        size_t i;
-
-        if (sz == 0)
-                return;
-
-        sz--;
-        for (i = 0; i < sz && src[i]; i++)
-                dst[i] = src[i];
-        dst[i] = '\0';
-}
-
 static int xsk_get_max_queues(struct xsk_socket *xsk)
 {
 	struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS };
@@ -552,7 +534,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 		return -errno;
 
 	ifr.ifr_data = (void *)&channels;
-	libbpf_strlcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ);
+	bpf_strlcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ);
 	err = ioctl(fd, SIOCETHTOOL, &ifr);
 	if (err && errno != EOPNOTSUPP) {
 		ret = -errno;
@@ -771,7 +753,7 @@ static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
 	}
 
 	ctx->ifindex = ifindex;
-	libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
+	bpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
 
 	xsk->ctx = ctx;
 	xsk->ctx->has_bpf_link = xsk_probe_bpf_link();
@@ -958,7 +940,7 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
 	ctx->refcount = 1;
 	ctx->umem = umem;
 	ctx->queue_id = queue_id;
-	libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
+	bpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
 
 	ctx->fill = fill;
 	ctx->comp = comp;
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 681a5db80dae..162d3a516f2c 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -1006,7 +1006,8 @@ static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fd
 {
 	struct xsk_socket_info *xsk = ifobject->xsk;
 	bool use_poll = ifobject->use_poll;
-	u32 i, idx = 0, ret, valid_pkts = 0;
+	u32 i, idx = 0, valid_pkts = 0;
+	int ret;
 
 	while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE) {
 		if (use_poll) {