linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Zhen Lei <thunder.leizhen@huawei.com>
To: Josh Poimboeuf <jpoimboe@kernel.org>,
	Jiri Kosina <jikos@kernel.org>, Miroslav Benes <mbenes@suse.cz>,
	Petr Mladek <pmladek@suse.com>,
	Joe Lawrence <joe.lawrence@redhat.com>,
	<live-patching@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	Masahiro Yamada <masahiroy@kernel.org>,
	Alexei Starovoitov <ast@kernel.org>, Jiri Olsa <jolsa@kernel.org>,
	Kees Cook <keescook@chromium.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	"Luis Chamberlain" <mcgrof@kernel.org>,
	<linux-modules@vger.kernel.org>,
	"Steven Rostedt" <rostedt@goodmis.org>,
	Ingo Molnar <mingo@redhat.com>
Cc: Zhen Lei <thunder.leizhen@huawei.com>
Subject: [PATCH v7 05/11] kallsyms: Improve the performance of kallsyms_lookup_name()
Date: Mon, 17 Oct 2022 14:49:44 +0800	[thread overview]
Message-ID: <20221017064950.2038-6-thunder.leizhen@huawei.com> (raw)
In-Reply-To: <20221017064950.2038-1-thunder.leizhen@huawei.com>

Currently, to search for a symbol, we need to expand the symbols in
'kallsyms_names' one by one, and then use the expanded string for
comparison. This process can be optimized.

And now scripts/kallsyms no longer compresses the symbol types, each
symbol type always occupies one byte. So we can first compress the
searched symbol and then make a quick comparison based on the compressed
length and content. In this way, for entries with mismatched lengths,
there is no need to expand and compare strings. And for those matching
lengths, there's no need to expand the symbol. This saves a lot of time.
According to my test results, the average performance of
kallsyms_lookup_name() can be improved by 20 to 30 times.

The pseudo code of the test case is as follows:
static int stat_find_name(...)
{
	start = sched_clock();
	(void)kallsyms_lookup_name(name);
	end = sched_clock();
	//Update min, max, cnt, sum
}

/*
 * Traverse all symbols in sequence and collect statistics on the time
 * taken by kallsyms_lookup_name() to lookup each symbol.
 */
kallsyms_on_each_symbol(stat_find_name, NULL);

The test results are as follows (twice):
After : min=5250, max=  726560, avg= 302132
After : min=5320, max=  726850, avg= 301978
Before: min=170,  max=15949190, avg=7553906
Before: min=160,  max=15877280, avg=7517784

The average time consumed is only 4.01% and the maximum time consumed is
only 4.57% of the time consumed before optimization.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
---
 kernel/kallsyms.c | 50 +++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 46 insertions(+), 4 deletions(-)

diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index f1fe404af184047..7f3987cc975be3b 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -107,7 +107,7 @@ static unsigned char *find_token(unsigned char *str, int len,
 	return NULL;
 }
 
-static int __maybe_unused kallsyms_compress_symbol_name(const char *name, char *buf, size_t size)
+static int kallsyms_compress_symbol_name(const char *name, char *buf, size_t size)
 {
 	int i, j, n, len;
 	unsigned char *p1, *p2;
@@ -267,23 +267,65 @@ static bool cleanup_symbol_name(char *s)
 	return false;
 }
 
+static int kallsyms_lookup_compressed_name(unsigned char *namebuf, int namelen,
+					   unsigned long *addr)
+{
+	unsigned int i, off;
+	unsigned int len, x;
+	const unsigned char *name;
+
+	for (i = 0, off = 0; namelen && i < kallsyms_num_syms; i++) {
+		/*
+		 * For each entry in kallsyms_names[], the storage format is:
+		 *  ----------------------------
+		 * | len(1-2) | type(1) | name(x) |
+		 *  ----------------------------
+		 *
+		 * Number of bytes in parentheses, and: len = 1 + x
+		 */
+		len = kallsyms_names[off];
+		off++;
+		if (len & 0x80) {
+			len = (len & 0x7f) | (kallsyms_names[off] << 7);
+			off++;
+		}
+		name = &kallsyms_names[off + 1];
+		off += len;
+
+		x = len - 1;
+		if (x != namelen)
+			continue;
+
+		if (!memcmp(name, namebuf, namelen)) {
+			*addr = kallsyms_sym_address(i);
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
 /* Lookup the address for this symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name)
 {
 	char namebuf[KSYM_NAME_LEN];
 	unsigned long i;
 	unsigned int off;
+	unsigned long addr;
+	int ret, len;
 
 	/* Skip the search for empty string. */
 	if (!*name)
 		return 0;
 
+	len = kallsyms_compress_symbol_name(name, namebuf, ARRAY_SIZE(namebuf));
+	ret = kallsyms_lookup_compressed_name(namebuf, len, &addr);
+	if (!ret)
+		return addr;
+
 	for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
 		off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
 
-		if (strcmp(namebuf, name) == 0)
-			return kallsyms_sym_address(i);
-
 		if (cleanup_symbol_name(namebuf) && strcmp(namebuf, name) == 0)
 			return kallsyms_sym_address(i);
 	}
-- 
2.25.1


  parent reply	other threads:[~2022-10-17  6:52 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-17  6:49 [PATCH v7 00/11] kallsyms: Optimizes the performance of lookup symbols Zhen Lei
2022-10-17  6:49 ` [PATCH v7 01/11] scripts/kallsyms: rename build_initial_tok_table() Zhen Lei
2022-10-17  6:49 ` [PATCH v7 02/11] scripts/kallsyms: don't compress symbol types Zhen Lei
2022-10-17  6:49 ` [PATCH v7 03/11] scripts/kallsyms: remove helper sym_name() and cleanup Zhen Lei
2022-10-17  6:49 ` [PATCH v7 04/11] kallsyms: Add helper kallsyms_compress_symbol_name() Zhen Lei
2022-10-17  6:49 ` Zhen Lei [this message]
2022-10-17  6:49 ` [PATCH v7 06/11] kallsyms: Improve the performance of kallsyms_lookup_name() when CONFIG_LTO_CLANG=y Zhen Lei
2022-10-17  6:49 ` [PATCH v7 07/11] kallsyms: Add helper kallsyms_on_each_match_symbol() Zhen Lei
2022-10-17  6:49 ` [PATCH v7 08/11] livepatch: Use kallsyms_on_each_match_symbol() to improve performance Zhen Lei
2022-10-17  6:49 ` [PATCH v7 09/11] livepatch: Improve the search performance of module_kallsyms_on_each_symbol() Zhen Lei
2022-10-17  6:49 ` [PATCH v7 10/11] kallsyms: Delete an unused parameter related to kallsyms_on_each_symbol() Zhen Lei
2022-10-17  6:49 ` [PATCH v7 11/11] kallsyms: Add self-test facility Zhen Lei
2022-10-18  8:21   ` kernel test robot
2022-10-18  9:11     ` Leizhen (ThunderTown)
2022-10-18  9:32   ` kernel test robot
2022-10-19  8:39     ` Leizhen (ThunderTown)
2022-10-21  2:00   ` kernel test robot
2022-10-19 12:01 ` [PATCH v7 00/11] kallsyms: Optimizes the performance of lookup symbols Luis Chamberlain
2022-10-19 14:11   ` Leizhen (ThunderTown)
2022-10-25 17:53     ` Luis Chamberlain
2022-10-26  6:44       ` Leizhen (ThunderTown)
2022-10-26 19:03         ` Luis Chamberlain
2022-10-27  3:26           ` Leizhen (ThunderTown)
2022-10-27  6:27             ` Leizhen (ThunderTown)
2022-10-29  8:10               ` Leizhen (ThunderTown)
2022-10-29 12:49                 ` David Laight
2022-10-31  2:55                   ` Leizhen (ThunderTown)
2022-10-31  4:55                 ` Leizhen (ThunderTown)
2022-10-31 15:04                   ` Leizhen (ThunderTown)
2022-11-02  9:18                     ` Leizhen (ThunderTown)

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=20221017064950.2038-6-thunder.leizhen@huawei.com \
    --to=thunder.leizhen@huawei.com \
    --cc=akpm@linux-foundation.org \
    --cc=ast@kernel.org \
    --cc=jikos@kernel.org \
    --cc=joe.lawrence@redhat.com \
    --cc=jolsa@kernel.org \
    --cc=jpoimboe@kernel.org \
    --cc=keescook@chromium.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-modules@vger.kernel.org \
    --cc=live-patching@vger.kernel.org \
    --cc=masahiroy@kernel.org \
    --cc=mbenes@suse.cz \
    --cc=mcgrof@kernel.org \
    --cc=mingo@redhat.com \
    --cc=pmladek@suse.com \
    --cc=rostedt@goodmis.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).