linux-kernel - [PATCH 2/2] lib kallsyms: parse using io api

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: <20200430193557.101831-3-irogers@google.com>
Date:   Thu, 30 Apr 2020 12:35:57 -0700
From:   Ian Rogers <irogers@...gle.com>
To:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Jiri Olsa <jolsa@...hat.com>,
        Namhyung Kim <namhyung@...nel.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        linux-kernel@...r.kernel.org
Cc:     Stephane Eranian <eranian@...gle.com>,
        Ian Rogers <irogers@...gle.com>
Subject: [PATCH 2/2] lib kallsyms: parse using io api

Perf record will call kallsyms__parse 4 times during startup and process
megabytes of data. This changes kallsyms__parse to use the io library
rather than fgets to improve performance of the user code by over 8%.

Before:
  Running 'internals/kallsyms-parse' benchmark:
  Average kallsyms__parse took: 103.988 ms (+- 0.203 ms)
After:
  Running 'internals/kallsyms-parse' benchmark:
  Average kallsyms__parse took: 95.571 ms (+- 0.006 ms)

For a workload like:
$ perf record /bin/true
Run under 'perf record -e cycles:u -g' the time goes from:
Before
30.10%     1.67%  perf     perf                [.] kallsyms__parse
After
25.55%    20.04%  perf     perf                [.] kallsyms__parse
So a little under 5% of the start-up time is removed. A lot of what
remains is on the kernel side, but caching kallsyms within perf would
at least impact memory footprint.

Signed-off-by: Ian Rogers <irogers@...gle.com>
---
 tools/lib/api/io.h          |  3 ++
 tools/lib/symbol/kallsyms.c | 81 +++++++++++++++++++------------------
 2 files changed, 44 insertions(+), 40 deletions(-)

diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
index b7e55b5f8a4a..777c20f6b604 100644
--- a/tools/lib/api/io.h
+++ b/tools/lib/api/io.h
@@ -7,6 +7,9 @@
 #ifndef __API_IO__
 #define __API_IO__
 
+#include <stdlib.h>
+#include <unistd.h>
+
 struct io {
 	/* File descriptor being read/ */
 	int fd;
diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
index 1a7a9f877095..1ef61b68332a 100644
--- a/tools/lib/symbol/kallsyms.c
+++ b/tools/lib/symbol/kallsyms.c
@@ -1,7 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "symbol/kallsyms.h"
+#include "api/io.h"
 #include <stdio.h>
-#include <stdlib.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 
 u8 kallsyms2elf_type(char type)
 {
@@ -28,61 +30,60 @@ int hex2u64(const char *ptr, u64 *long_val)
 	return p - ptr;
 }
 
+static void read_to_eol(struct io *io)
+{
+	int ch;
+
+	for (;;) {
+		ch = io__get_char(io);
+		if (ch < 0 || ch == '\n')
+			return;
+	}
+}
+
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
 					  char type, u64 start))
 {
-	char *line = NULL;
-	size_t n;
-	int err = -1;
-	FILE *file = fopen(filename, "r");
+	struct io io;
+	char bf[BUFSIZ];
 
-	if (file == NULL)
-		goto out_failure;
+	io.fd = open(filename, O_RDONLY, 0);
 
-	err = 0;
-
-	while (!feof(file)) {
-		u64 start;
-		int line_len, len;
-		char symbol_type;
-		char *symbol_name;
-
-		line_len = getline(&line, &n, file);
-		if (line_len < 0 || !line)
-			break;
+	if (io.fd < 0)
+		return -1;
 
-		line[--line_len] = '\0'; /* \n */
+	io__init(&io, io.fd, bf, sizeof(bf));
 
-		len = hex2u64(line, &start);
+	while (!io.eof) {
+		__u64 start;
+		int ch, err;
+		size_t i;
+		char symbol_type;
+		char symbol_name[KSYM_NAME_LEN + 1];
 
-		/* Skip the line if we failed to parse the address. */
-		if (!len)
+		if (io__get_hex(&io, &start) != ' ') {
+			read_to_eol(&io);
 			continue;
-
-		len++;
-		if (len + 2 >= line_len)
+		}
+		symbol_type = io__get_char(&io);
+		if (io__get_char(&io) != ' ') {
+			read_to_eol(&io);
 			continue;
-
-		symbol_type = line[len];
-		len += 2;
-		symbol_name = line + len;
-		len = line_len - len;
-
-		if (len >= KSYM_NAME_LEN) {
-			err = -1;
-			break;
 		}
+		for (i = 0; i < sizeof(symbol_name); i++) {
+			ch = io__get_char(&io);
+			if (ch < 0 || ch == '\n')
+				break;
+			symbol_name[i]  = ch;
+		}
+		symbol_name[i]  = '\0';
 
 		err = process_symbol(arg, symbol_name, symbol_type, start);
 		if (err)
 			break;
 	}
 
-	free(line);
-	fclose(file);
-	return err;
-
-out_failure:
-	return -1;
+	close(io.fd);
+	return 0;
 }
-- 
2.26.2.526.g744177e7f7-goog