[PATCH v2 05/18] perf db-export: Store symbol database IDs in a hashmap

[Ian Rogers]

Currently, db-export reserves sizeof(u64) bytes ahead of every allocated
struct symbol via symbol_conf.priv_size and accesses the database ID at
a negative offset via symbol__priv(). This adds 8 bytes to every loaded
symbol across all DSOs even when only a subset of symbols are exported,
and negative-offset pointer arithmetic ahead of struct symbol is
incompatible with wrapping struct symbol in DECLARE_RC_STRUCT(symbol).

Store exported symbol database IDs in an on-demand sym_db_ids hashmap in
struct db_export instead of using symbol__priv().

Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/util/db-export.c | 68 ++++++++++++++++++++++++++++++-------
 tools/perf/util/db-export.h |  8 +++++
 2 files changed, 63 insertions(+), 13 deletions(-)

diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 732369fe0046..6ebc060bdb8f 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -4,21 +4,37 @@
  * Copyright (c) 2014, Intel Corporation.
  */
 
+#include "db-export.h"
+
 #include <errno.h>
+#include <stdbool.h>
+#include <stddef.h>
 #include <stdlib.h>
 
+#include <linux/err.h>
+
+#include "call-path.h"
+#include "callchain.h"
+#include "comm.h"
 #include "dso.h"
+#include "event.h"
 #include "evsel.h"
+#include "hashmap.h"
 #include "machine.h"
-#include "thread.h"
-#include "comm.h"
-#include "symbol.h"
 #include "map.h"
-#include "event.h"
+#include "symbol.h"
 #include "thread-stack.h"
-#include "callchain.h"
-#include "call-path.h"
-#include "db-export.h"
+#include "thread.h"
+
+static size_t sym_ptr_hash(long key, void *ctx __maybe_unused)
+{
+	return hash_bits((size_t)key, 16);
+}
+
+static bool sym_ptr_equal(long key1, long key2, void *ctx __maybe_unused)
+{
+	return key1 == key2;
+}
 
 int db_export__init(struct db_export *dbe)
 {
@@ -28,6 +44,8 @@ int db_export__init(struct db_export *dbe)
 
 void db_export__exit(struct db_export *dbe)
 {
+	hashmap__free(dbe->sym_db_ids);
+	dbe->sym_db_ids = NULL;
 	call_return_processor__free(dbe->crp);
 	dbe->crp = NULL;
 }
@@ -156,15 +174,41 @@ int db_export__dso(struct db_export *dbe, struct dso *dso,
 	return 0;
 }
 
+/*
+ * Return the database export ID assigned to @sym in @dbe->sym_db_ids, or 0
+ * if @sym has not been exported yet.
+ */
+u64 db_export__symbol_db_id(struct db_export *dbe, struct symbol *sym)
+{
+	long db_id = 0;
+
+	if (sym && dbe->sym_db_ids)
+		hashmap__find(dbe->sym_db_ids, (long)sym, &db_id);
+	return (u64)db_id;
+}
+
 int db_export__symbol(struct db_export *dbe, struct symbol *sym,
 		      struct dso *dso)
 {
-	u64 *sym_db_id = symbol__priv(sym);
+	long db_id;
 
-	if (*sym_db_id)
+	if (db_export__symbol_db_id(dbe, sym))
 		return 0;
 
-	*sym_db_id = ++dbe->symbol_last_db_id;
+	if (!dbe->sym_db_ids) {
+		dbe->sym_db_ids =
+			hashmap__new(sym_ptr_hash, sym_ptr_equal, NULL);
+		if (IS_ERR(dbe->sym_db_ids)) {
+			int err = PTR_ERR(dbe->sym_db_ids);
+
+			dbe->sym_db_ids = NULL;
+			return err;
+		}
+	}
+
+	db_id = ++dbe->symbol_last_db_id;
+	if (hashmap__set(dbe->sym_db_ids, (long)sym, db_id, NULL, NULL))
+		return -ENOMEM;
 
 	if (dbe->export_symbol)
 		return dbe->export_symbol(dbe, sym, dso);
@@ -192,12 +236,10 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
 		}
 
 		if (al->sym) {
-			u64 *db_id = symbol__priv(al->sym);
-
 			err = db_export__symbol(dbe, al->sym, dso);
 			if (err)
 				return err;
-			*sym_db_id = *db_id;
+			*sym_db_id = db_export__symbol_db_id(dbe, al->sym);
 			*offset = al->addr - symbol__start(al->sym);
 		}
 	}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index 1abbfd398e3a..2e0cf2dfa281 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -21,6 +21,8 @@ struct call_return_processor;
 struct call_path_root;
 struct call_path;
 struct call_return;
+struct hashmap;
+struct symbol;
 
 struct export_sample {
 	union perf_event	*event;
@@ -63,6 +65,11 @@ struct db_export {
 				     u64 th_in_id, u64 comm_in_id, int flags);
 	struct call_return_processor *crp;
 	struct call_path_root *cpr;
+	/**
+	 * @sym_db_ids: Hashmap mapping struct symbol pointers to their
+	 * exported 64-bit database IDs.
+	 */
+	struct hashmap *sym_db_ids;
 	u64 evsel_last_db_id;
 	u64 machine_last_db_id;
 	u64 thread_last_db_id;
@@ -90,6 +97,7 @@ int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
 			   struct thread *thread);
 int db_export__dso(struct db_export *dbe, struct dso *dso,
 		   struct machine *machine);
+u64 db_export__symbol_db_id(struct db_export *dbe, struct symbol *sym);
 int db_export__symbol(struct db_export *dbe, struct symbol *sym,
 		      struct dso *dso);
 int db_export__branch_type(struct db_export *dbe, u32 branch_type,
-- 
2.56.0.313.g2479322e68-goog