linux-kernel - [PATCH v2 1/4] perf annotate: Add a hashmap for symbol histogram

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20240304230815.1440583-2-namhyung@kernel.org>
Date: Mon,  4 Mar 2024 15:08:12 -0800
From: Namhyung Kim <namhyung@...nel.org>
To: Arnaldo Carvalho de Melo <acme@...nel.org>,
	Ian Rogers <irogers@...gle.com>
Cc: Jiri Olsa <jolsa@...nel.org>,
	Adrian Hunter <adrian.hunter@...el.com>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...nel.org>,
	LKML <linux-kernel@...r.kernel.org>,
	linux-perf-users@...r.kernel.org,
	Andi Kleen <ak@...ux.intel.com>
Subject: [PATCH v2 1/4] perf annotate: Add a hashmap for symbol histogram

Now symbol histogram uses an array to save per-offset sample counts.
But it wastes a lot of memory if the symbol has a few samples only.
Add a hashmap to save values only for actual samples.

For now, it has duplicate histogram (one in the existing array and
another in the new hash map).  Once it can convert to use the hash
in all places, we can get rid of the array later.

Reviewed-by: Ian Rogers <irogers@...gle.com>
Signed-off-by: Namhyung Kim <namhyung@...nel.org>
---
 tools/perf/util/annotate.c | 42 ++++++++++++++++++++++++++++++++++++--
 tools/perf/util/annotate.h |  2 ++
 2 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 107b264fa41e..caaea9421235 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -38,6 +38,7 @@
 #include "arch/common.h"
 #include "namespaces.h"
 #include "thread.h"
+#include "hashmap.h"
 #include <regex.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
@@ -863,6 +864,17 @@ bool arch__is(struct arch *arch, const char *name)
 	return !strcmp(arch->name, name);
 }
 
+/* symbol histogram: key = offset << 16 | evsel->core.idx */
+static size_t sym_hist_hash(long key, void *ctx __maybe_unused)
+{
+	return (key >> 16) + (key & 0xffff);
+}
+
+static bool sym_hist_equal(long key1, long key2, void *ctx __maybe_unused)
+{
+	return key1 == key2;
+}
+
 static struct annotated_source *annotated_source__new(void)
 {
 	struct annotated_source *src = zalloc(sizeof(*src));
@@ -877,6 +889,8 @@ static __maybe_unused void annotated_source__delete(struct annotated_source *src
 {
 	if (src == NULL)
 		return;
+
+	hashmap__free(src->samples);
 	zfree(&src->histograms);
 	free(src);
 }
@@ -909,6 +923,14 @@ static int annotated_source__alloc_histograms(struct annotated_source *src,
 	src->sizeof_sym_hist = sizeof_sym_hist;
 	src->nr_histograms   = nr_hists;
 	src->histograms	     = calloc(nr_hists, sizeof_sym_hist) ;
+
+	if (src->histograms == NULL)
+		return -1;
+
+	src->samples = hashmap__new(sym_hist_hash, sym_hist_equal, NULL);
+	if (src->samples == NULL)
+		zfree(&src->histograms);
+
 	return src->histograms ? 0 : -1;
 }
 
@@ -920,6 +942,7 @@ void symbol__annotate_zero_histograms(struct symbol *sym)
 	if (notes->src != NULL) {
 		memset(notes->src->histograms, 0,
 		       notes->src->nr_histograms * notes->src->sizeof_sym_hist);
+		hashmap__clear(notes->src->samples);
 	}
 	if (notes->branch && notes->branch->cycles_hist) {
 		memset(notes->branch->cycles_hist, 0,
@@ -983,8 +1006,10 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms,
 				      struct perf_sample *sample)
 {
 	struct symbol *sym = ms->sym;
-	unsigned offset;
+	long hash_key;
+	u64 offset;
 	struct sym_hist *h;
+	struct sym_hist_entry *entry;
 
 	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map__unmap_ip(ms->map, addr));
 
@@ -1002,15 +1027,28 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms,
 			 __func__, __LINE__, sym->name, sym->start, addr, sym->end, sym->type == STT_FUNC);
 		return -ENOMEM;
 	}
+
+	hash_key = offset << 16 | evidx;
+	if (!hashmap__find(src->samples, hash_key, &entry)) {
+		entry = zalloc(sizeof(*entry));
+		if (entry == NULL)
+			return -ENOMEM;
+
+		if (hashmap__add(src->samples, hash_key, entry) < 0)
+			return -ENOMEM;
+	}
+
 	h->nr_samples++;
 	h->addr[offset].nr_samples++;
 	h->period += sample->period;
 	h->addr[offset].period += sample->period;
+	entry->nr_samples++;
+	entry->period += sample->period;
 
 	pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64
 		  ", evidx=%d] => nr_samples: %" PRIu64 ", period: %" PRIu64 "\n",
 		  sym->start, sym->name, addr, addr - sym->start, evidx,
-		  h->addr[offset].nr_samples, h->addr[offset].period);
+		  entry->nr_samples, entry->period);
 	return 0;
 }
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 94435607c958..a2b0c8210740 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -12,6 +12,7 @@
 #include "symbol_conf.h"
 #include "mutex.h"
 #include "spark.h"
+#include "hashmap.h"
 
 struct hist_browser_timer;
 struct hist_entry;
@@ -280,6 +281,7 @@ struct annotated_source {
 	size_t			sizeof_sym_hist;
 	struct sym_hist		*histograms;
 	struct annotation_line	**offsets;
+	struct hashmap	   	*samples;
 	int    			nr_histograms;
 	int			nr_entries;
 	int			nr_asm_entries;
-- 
2.44.0.rc1.240.g4c46232300-goog