All of lore.kernel.org
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Alan Maguire <alan.maguire@oracle.com>
Cc: Jiri Olsa <jolsa@kernel.org>,
	Clark Williams <williams@redhat.com>,
	dwarves@vger.kernel.org,
	Arnaldo Carvalho de Melo <acme@redhat.com>
Subject: [PATCH 3/7] dwarf_loader: Initial support for DW_TAG_subprogram in DW_TAG_enumeration
Date: Thu, 18 Jun 2026 14:33:12 -0300	[thread overview]
Message-ID: <20260618173316.83598-4-acme@kernel.org> (raw)
In-Reply-To: <20260618173316.83598-1-acme@kernel.org>

From: Arnaldo Carvalho de Melo <acme@redhat.com>

In Rust enums can have subprograms, add initial support for it.

Example of a Rust enumeration with a DW_TAG_subprogram tag.

  $ pahole -C ProgramKind /tmp/build/perf-tools-next/tests/workloads/code_with_type.a
  enum ProgramKind {
  	PathLookup = 0,
  	Relative   = 1,
  	Absolute   = 2,
  	enum ProgramKind new(struct &std::ffi::os_str::OsStr),
  } __attribute__((__packed__));
  $

Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 btf_encoder.c     | 13 +++++++++----
 ctf_encoder.c     | 16 +++++++++++-----
 dwarf_loader.c    | 39 +++++++++++++++++++++++++++++++--------
 dwarves.c         |  3 +++
 dwarves.h         |  2 +-
 dwarves_emit.c    | 10 +++++-----
 dwarves_fprintf.c | 44 ++++++++++++++++++++++++++++++++------------
 pahole.c          |  9 ++++++---
 8 files changed, 98 insertions(+), 38 deletions(-)

diff --git a/btf_encoder.c b/btf_encoder.c
index 633bc6162ce013d0..be880f3fdb32f792 100644
--- a/btf_encoder.c
+++ b/btf_encoder.c
@@ -1786,7 +1786,7 @@ static uint32_t array_type__nelems(struct tag *tag)
 }
 
 static int32_t btf_encoder__add_enum_type(struct btf_encoder *encoder, struct tag *tag,
-					  struct conf_load *conf_load)
+					  const struct cu *cu, struct conf_load *conf_load)
 {
 	struct type *etype = tag__type(tag);
 	struct enumerator *pos;
@@ -1798,6 +1798,11 @@ static int32_t btf_encoder__add_enum_type(struct btf_encoder *encoder, struct ta
 		return type_id;
 
 	type__for_each_enumerator(etype, pos) {
+		if (pos->tag.tag != DW_TAG_enumerator) {
+			fprintf(stderr, "Unexpected DW_TAG_%s <%llx>, skipping it...\n",
+				dwarf_tag_name(tag->tag), tag__orig_id(tag, cu));
+			continue;
+		}
 		name = enumerator__name(pos);
 		if (btf_encoder__add_enum_val(encoder, name, pos->value, etype, conf_load))
 			return -1;
@@ -1807,7 +1812,7 @@ static int32_t btf_encoder__add_enum_type(struct btf_encoder *encoder, struct ta
 }
 
 static int btf_encoder__encode_tag(struct btf_encoder *encoder, struct tag *tag,
-				   struct conf_load *conf_load)
+				   const struct cu *cu, struct conf_load *conf_load)
 {
 	/* single out type 0 as it represents special type "void" */
 	uint32_t ref_type_id = tag->type == 0 ? 0 : encoder->type_id_off + tag->type;
@@ -1846,7 +1851,7 @@ static int btf_encoder__encode_tag(struct btf_encoder *encoder, struct tag *tag,
 		encoder->need_index_type = true;
 		return btf_encoder__add_array(encoder, ref_type_id, encoder->array_index_id, array_type__nelems(tag));
 	case DW_TAG_enumeration_type:
-		return btf_encoder__add_enum_type(encoder, tag, conf_load);
+		return btf_encoder__add_enum_type(encoder, tag, cu, conf_load);
 	case DW_TAG_subroutine_type:
 		return btf_encoder__add_func_proto_for_ftype(encoder, tag__ftype(tag));
         case DW_TAG_unspecified_type:
@@ -2905,7 +2910,7 @@ int btf_encoder__encode_cu(struct btf_encoder *encoder, struct cu *cu, struct co
 	}
 
 	cu__for_each_type(cu, core_id, pos) {
-		btf_type_id = btf_encoder__encode_tag(encoder, pos, conf_load);
+		btf_type_id = btf_encoder__encode_tag(encoder, pos, cu, conf_load);
 
 		if (btf_type_id == 0) {
 			++skipped_types;
diff --git a/ctf_encoder.c b/ctf_encoder.c
index b761287d45348c59..1c61c76ba20e06bc 100644
--- a/ctf_encoder.c
+++ b/ctf_encoder.c
@@ -142,7 +142,7 @@ static int subroutine_type__encode(struct tag *tag, uint32_t core_id, struct ctf
 	return 0;
 }
 
-static int enumeration_type__encode(struct tag *tag, uint32_t core_id, struct ctf *ctf)
+static int enumeration_type__encode(struct tag *tag, const struct cu *cu, uint32_t core_id, struct ctf *ctf)
 {
 	struct type *etype = tag__type(tag);
 	int64_t position;
@@ -154,13 +154,19 @@ static int enumeration_type__encode(struct tag *tag, uint32_t core_id, struct ct
 		return -1;
 
 	struct enumerator *pos;
-	type__for_each_enumerator(etype, pos)
+	type__for_each_enumerator(etype, pos) {
+		if (pos->tag.tag != DW_TAG_enumerator) {
+			fprintf(stderr, "Unexpected DW_TAG_%s <%llx>, skipping it...\n",
+				dwarf_tag_name(tag->tag), tag__orig_id(tag, cu));
+			continue;
+		}
 		ctf__add_enumerator(ctf, pos->name, pos->value, &position);
+	}
 
 	return 0;
 }
 
-static void tag__encode_ctf(struct tag *tag, uint32_t core_id, struct ctf *ctf)
+static void tag__encode_ctf(struct tag *tag, const struct cu *cu, uint32_t core_id, struct ctf *ctf)
 {
 	switch (tag->tag) {
 	case DW_TAG_base_type:
@@ -190,7 +196,7 @@ static void tag__encode_ctf(struct tag *tag, uint32_t core_id, struct ctf *ctf)
 		subroutine_type__encode(tag, core_id, ctf);
 		break;
 	case DW_TAG_enumeration_type:
-		enumeration_type__encode(tag, core_id, ctf);
+		enumeration_type__encode(tag, cu, core_id, ctf);
 		break;
 	}
 }
@@ -253,7 +259,7 @@ int cu__encode_ctf(struct cu *cu, int verbose)
 	uint32_t id;
 	struct tag *pos;
 	cu__for_each_type(cu, id, pos)
-		tag__encode_ctf(pos, id, ctf);
+		tag__encode_ctf(pos, cu, id, ctf);
 
 	struct hlist_head hash_addr[HASHADDR__SIZE];
 
diff --git a/dwarf_loader.c b/dwarf_loader.c
index 54cc66748ef685fc..2a62059dc66517dc 100644
--- a/dwarf_loader.c
+++ b/dwarf_loader.c
@@ -1943,6 +1943,8 @@ out_delete:
 	return NULL;
 }
 
+static struct tag *die__create_new_function(Dwarf_Die *die, struct cu *cu, struct conf_load *conf);
+
 static struct tag *die__create_new_enumeration(Dwarf_Die *die, struct cu *cu, struct conf_load *conf)
 {
 	Dwarf_Die child;
@@ -1964,18 +1966,39 @@ static struct tag *die__create_new_enumeration(Dwarf_Die *die, struct cu *cu, st
 
 	die = &child;
 	do {
-		struct enumerator *enumerator;
+		switch (dwarf_tag(die)) {
+		case DW_TAG_enumerator: {
+			struct enumerator *enumerator = enumerator__new(die, cu, conf);
+
+			if (enumerator == NULL)
+				goto out_delete;
+
+			enumeration__add(enumeration, enumerator);
+			cu__hash(cu, &enumerator->tag);
+		}
+			continue;
+		case DW_TAG_subprogram: {
+			struct tag *tag = die__create_new_function(die, cu, conf);
+			uint32_t id;
+
+			if (tag == NULL)
+				goto out_delete;
+
+			if (cu__table_add_tag(cu, tag, &id) < 0) {
+				tag__delete(tag, cu);
+				goto out_delete;
+			}
 
-		if (dwarf_tag(die) != DW_TAG_enumerator) {
+			struct dwarf_tag *dtag = tag__dwarf(tag);
+			dtag->small_id = id;
+			namespace__add_tag(&enumeration->namespace, tag);
+			cu__hash(cu, tag);
+			break;
+		}
+		default:
 			cu__tag_not_handled(cu, die);
 			continue;
 		}
-		enumerator = enumerator__new(die, cu, conf);
-		if (enumerator == NULL)
-			goto out_delete;
-
-		enumeration__add(enumeration, enumerator);
-		cu__hash(cu, &enumerator->tag);
 	} while (dwarf_siblingof(die, die) == 0);
 out:
 	return &enumeration->namespace.tag;
diff --git a/dwarves.c b/dwarves.c
index 37f769ee65caad72..2af10588ff2f20c5 100644
--- a/dwarves.c
+++ b/dwarves.c
@@ -2015,6 +2015,9 @@ static void enumeration__calc_prefix(struct type *enumeration)
 	struct enumerator *entry;
 
 	type__for_each_enumerator(enumeration, entry) {
+		if (entry->tag.tag != DW_TAG_enumerator)
+			continue;
+
 		const char *curr_name = enumerator__name(entry);
 
 		if (previous_name) {
diff --git a/dwarves.h b/dwarves.h
index 6595c16434966f09..6ad2995d2e33be0d 100644
--- a/dwarves.h
+++ b/dwarves.h
@@ -1646,7 +1646,7 @@ static inline const char *enumerator__name(const struct enumerator *enumerator)
 
 void enumeration__delete(struct type *type, struct cu *cu);
 void enumeration__add(struct type *type, struct enumerator *enumerator);
-size_t enumeration__fprintf(const struct tag *tag_enum,
+size_t enumeration__fprintf(const struct tag *tag_enum, const struct cu *cu,
 			    const struct conf_fprintf *conf, FILE *fp);
 
 int dwarves__init(void);
diff --git a/dwarves_emit.c b/dwarves_emit.c
index 01b33b7ec41eb947..aaf0f8f9a7ea815a 100644
--- a/dwarves_emit.c
+++ b/dwarves_emit.c
@@ -100,7 +100,7 @@ static struct type *type_emissions__find_fwd_decl(const struct type_emissions *e
 	return NULL;
 }
 
-static int enumeration__emit_definitions(struct tag *tag,
+static int enumeration__emit_definitions(struct tag *tag, const struct cu *cu,
 					 struct type_emissions *emissions,
 					 const struct conf_fprintf *conf,
 					 FILE *fp)
@@ -121,7 +121,7 @@ static int enumeration__emit_definitions(struct tag *tag,
 		return 0;
 	}
 
-	enumeration__fprintf(tag, conf, fp);
+	enumeration__fprintf(tag, cu, conf, fp);
 	fputs(";\n", fp);
 
 	// See comment on enumeration__fprintf(), it seems this happens with DWARF as well
@@ -198,10 +198,10 @@ static int typedef__emit_definitions(struct tag *tdef, struct cu *cu,
 		if (type__name(ctype) == NULL) {
 			fputs("typedef ", fp);
 			conf.suffix = type__name(def);
-			enumeration__emit_definitions(type, emissions, &conf, fp);
+			enumeration__emit_definitions(type, cu, emissions, &conf, fp);
 			goto out;
 		} else
-			enumeration__emit_definitions(type, emissions, &conf, fp);
+			enumeration__emit_definitions(type, cu, emissions, &conf, fp);
 	}
 		break;
 	case DW_TAG_structure_type:
@@ -380,7 +380,7 @@ next_indirection:
 			struct conf_fprintf conf = {
 				.suffix = NULL,
 			};
-			return enumeration__emit_definitions(type, emissions, &conf, fp);
+			return enumeration__emit_definitions(type, cu, emissions, &conf, fp);
 		}
 		break;
 	case DW_TAG_structure_type:
diff --git a/dwarves_fprintf.c b/dwarves_fprintf.c
index 1ec478c2a027be10..a3c8b391b9222fcd 100644
--- a/dwarves_fprintf.c
+++ b/dwarves_fprintf.c
@@ -153,6 +153,8 @@ const char tabs[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t";
 
 static size_t union__fprintf(struct type *type, const struct cu *cu,
 			     const struct conf_fprintf *conf, FILE *fp);
+static size_t function__fprintf(const struct tag *tag, const struct cu *cu,
+				const struct conf_fprintf *conf, FILE *fp);
 
 /*
  * In dwarves_emit.c we can call type__emit() using a locally setup conf_fprintf for which
@@ -404,7 +406,7 @@ next_type:
 		struct conf_fprintf tconf = *pconf;
 
 		tconf.suffix = type__name(type);
-		return printed + enumeration__fprintf(tag_type, &tconf, fp);
+		return printed + enumeration__fprintf(tag_type, cu, &tconf, fp);
 	}
 	}
 
@@ -448,7 +450,12 @@ static int enumeration__max_entry_name_len(struct type *type)
 	struct enumerator *pos;
 
 	type__for_each_enumerator(type, pos) {
-		int len = strlen(enumerator__name(pos));
+		int len = 0;
+
+		if (pos->tag.tag == DW_TAG_enumerator)
+			len = strlen(enumerator__name(pos));
+		else if (pos->tag.tag == DW_TAG_subprogram)
+			len = strlen(function__name(tag__function(&pos->tag)));
 
 		if (type->max_tag_name_len < len)
 			type->max_tag_name_len = len;
@@ -457,7 +464,8 @@ out:
 	return type->max_tag_name_len;
 }
 
-size_t enumeration__fprintf(const struct tag *tag, const struct conf_fprintf *conf, FILE *fp)
+size_t enumeration__fprintf(const struct tag *tag, const struct cu *cu,
+			    const struct conf_fprintf *conf, FILE *fp)
 {
 	struct type *type = tag__type(tag);
 	struct enumerator *pos;
@@ -478,13 +486,25 @@ size_t enumeration__fprintf(const struct tag *tag, const struct conf_fprintf *co
 	}
 
 	type__for_each_enumerator(type, pos) {
-		printed += fprintf(fp, "%.*s\t%-*s = ", indent, tabs,
-				   max_entry_name_len, enumerator__name(pos));
-		if (conf->hex_fmt)
-			printed += fprintf(fp, "%#llx", (unsigned long long)pos->value);
-		else
-			printed += fprintf(fp, type->is_signed_enum ?  "%lld" : "%llu",
-					   (unsigned long long)pos->value);
+		printed += fprintf(fp, "%.*s\t", indent, tabs);
+
+		switch (pos->tag.tag) {
+		case DW_TAG_subprogram:
+			function__fprintf(&pos->tag, cu, conf, fp);
+			break;
+		case DW_TAG_enumerator:
+			printed += fprintf(fp, "%-*s = ", max_entry_name_len, enumerator__name(pos));
+			if (conf->hex_fmt)
+				printed += fprintf(fp, "%#llx", (unsigned long long)pos->value);
+			else
+				printed += fprintf(fp, type->is_signed_enum ?  "%lld" : "%llu",
+						   (unsigned long long)pos->value);
+			break;
+		default:
+			printed += fprintf(fp, "/* Unexpected %s <%llx> */\n", dwarf_tag_name(tag->tag),
+					   tag__orig_id(tag, cu));
+			continue;
+		}
 		printed += fprintf(fp, ",\n");
 	}
 
@@ -934,7 +954,7 @@ print_modifier: {
 		if (type__name(ctype) != NULL && !expand_types)
 			printed += fprintf(fp, "enum %-*s %s", tconf.type_spacing - 5, type__name(ctype), name ?: "");
 		else
-			printed += enumeration__fprintf(type, &tconf, fp);
+			printed += enumeration__fprintf(type, cu, &tconf, fp);
 		break;
 	case DW_TAG_LLVM_annotation: {
 		struct tag *ttype = cu__type(cu, type->type);
@@ -2158,7 +2178,7 @@ size_t tag__fprintf(struct tag *tag, const struct cu *cu,
 		printed += array_type__fprintf(tag, cu, "array", pconf, fp);
 		break;
 	case DW_TAG_enumeration_type:
-		printed += enumeration__fprintf(tag, pconf, fp);
+		printed += enumeration__fprintf(tag, cu, pconf, fp);
 		break;
 	case DW_TAG_typedef:
 		printed += typedef__fprintf(tag, cu, pconf, fp);
diff --git a/pahole.c b/pahole.c
index 28d8f8832773520b..765da575f3dab39a 100644
--- a/pahole.c
+++ b/pahole.c
@@ -2155,7 +2155,7 @@ static const char *enumeration__lookup_value(struct type *enumeration, uint64_t
 	struct enumerator *entry;
 
 	type__for_each_enumerator(enumeration, entry) {
-		if (entry->value == value)
+		if (entry->tag.tag == DW_TAG_enumerator && entry->value == value)
 			return enumerator__name(entry);
 	}
 
@@ -2180,7 +2180,7 @@ static struct enumerator *enumeration__lookup_entry_from_value(struct type *enum
 	struct enumerator *entry;
 
 	type__for_each_enumerator(enumeration, entry) {
-		if (entry->value == value)
+		if (entry->tag.tag == DW_TAG_enumerator && entry->value == value)
 			return entry;
 	}
 
@@ -2206,6 +2206,9 @@ static struct enumerator *enumeration__find_enumerator(struct type *enumeration,
 	struct enumerator *entry;
 
 	type__for_each_enumerator(enumeration, entry) {
+		if (entry->tag.tag != DW_TAG_enumerator)
+			continue;
+
 		const char *entry_name = enumerator__name(entry);
 
 		if (!strcmp(entry_name, name))
@@ -3204,7 +3207,7 @@ static bool print_enumeration_with_enumerator(struct cu *cu, const char *name)
 
 	cu__for_each_enumeration(cu, id, enumeration) {
 		if (enumeration__find_enumerator(enumeration, name) != NULL) {
-			enumeration__fprintf(type__tag(enumeration), &conf, stdout);
+			enumeration__fprintf(type__tag(enumeration), cu, &conf, stdout);
 			fputc('\n', stdout);
 			return true;
 		}
-- 
2.54.0


  parent reply	other threads:[~2026-06-18 17:33 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-18 17:33 [PATCHES v2 0/7] Initial support for some Rust tags + way to ask for CU merging at load time Arnaldo Carvalho de Melo
2026-06-18 17:33 ` [PATCH 1/7] dwarf_loader: Initial support for DW_TAG_variant_part Arnaldo Carvalho de Melo
2026-06-18 17:33 ` [PATCH 2/7] dwarf_loader: Allow forcing the merge of CUs for solving inter CU tag references Arnaldo Carvalho de Melo
2026-06-18 17:33 ` Arnaldo Carvalho de Melo [this message]
2026-06-18 17:33 ` [PATCH 4/7] encoders: Fix diagnostic messages for unexpected tags in enumerations Arnaldo Carvalho de Melo
2026-06-18 17:33 ` [PATCH 5/7] dwarves_fprintf: Accumulate function__fprintf return value in enumeration printing Arnaldo Carvalho de Melo
2026-06-18 17:33 ` [PATCH 6/7] dwarves: Use tag__delete for enumeration children Arnaldo Carvalho de Melo
2026-06-18 17:33 ` [PATCH 7/7] btf_encoder: Remove unused variables Arnaldo Carvalho de Melo
  -- strict thread matches above, loose matches on Subject: below --
2026-06-18 15:15 [PATCHES v2 0/7] Initial support for some Rust tags + way to ask for CU merging at load time Arnaldo Carvalho de Melo
2026-06-18 15:16 ` [PATCH 3/7] dwarf_loader: Initial support for DW_TAG_subprogram in DW_TAG_enumeration Arnaldo Carvalho de Melo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260618173316.83598-4-acme@kernel.org \
    --to=acme@kernel.org \
    --cc=acme@redhat.com \
    --cc=alan.maguire@oracle.com \
    --cc=dwarves@vger.kernel.org \
    --cc=jolsa@kernel.org \
    --cc=williams@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.