Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
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 v5 06/10] kallsyms: Add helper kallsyms_on_each_match_symbol()
Date:   Fri, 23 Sep 2022 19:20:29 +0800
Message-ID: <20220923112033.1958-7-thunder.leizhen@huawei.com>
In-Reply-To: <20220923112033.1958-1-thunder.leizhen@huawei.com>
References: <20220923112033.1958-1-thunder.leizhen@huawei.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

Function kallsyms_on_each_symbol() traverses all symbols and submits each
symbol to the hook 'fn' for judgment and processing. For some cases, the
hook actually only handles the matched symbol, such as livepatch.

So that, we can first compress the name being looked up and then use
it for comparison when traversing 'kallsyms_names', this greatly reduces
the time consumed by traversing.

The pseudo code of the test case is as follows:
static int tst_find(void *data, const char *name,
		    struct module *mod, unsigned long addr)
{
	if (strcmp(name, "vmap") == 0)
		*(unsigned long *)data = addr;
        return 0;
}

static int tst_match(void *data, unsigned long addr)
{
        *(unsigned long *)data = addr;
        return 0;
}

start = sched_clock();
kallsyms_on_each_match_symbol(tst_match, "vmap", &addr);
end = sched_clock();

start = sched_clock();
kallsyms_on_each_symbol(tst_find, &addr);
end = sched_clock();

The test results are as follows (twice):
kallsyms_on_each_match_symbol:   557400,   583900
kallsyms_on_each_symbol      : 16659500, 16113950

kallsyms_on_each_match_symbol() consumes only 3.48% of
kallsyms_on_each_symbol()'s time.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
---
 include/linux/kallsyms.h |  8 ++++++++
 kernel/kallsyms.c        | 44 ++++++++++++++++++++++++++++++++++++----
 2 files changed, 48 insertions(+), 4 deletions(-)

diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index ad39636e0c3f122..2138219ae0296e9 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -69,6 +69,8 @@ static inline void *dereference_symbol_descriptor(void *ptr)
 int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
 				      unsigned long),
 			    void *data);
+int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long),
+				  const char *name, void *data);
 
 /* Lookup the address for a symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name);
@@ -168,6 +170,12 @@ static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long),
+						const char *name, void *data)
+{
+	return -EOPNOTSUPP;
+}
 #endif /*CONFIG_KALLSYMS*/
 
 static inline void print_ip_sym(const char *loglvl, unsigned long ip)
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index dcf5bdc7309a6cc..398865f01360589 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -266,14 +266,17 @@ static bool cleanup_symbol_name(char *s)
 	return false;
 }
 
-static int kallsyms_lookup_compressed_name(unsigned char *namebuf, int len,
-					   unsigned long *addr)
+static int __kallsyms_lookup_compressed_name(unsigned char *namebuf, int len,
+					     unsigned int *index,
+					     unsigned int *offset,
+					     unsigned long *addr)
 {
-	unsigned int i, off;
+	unsigned int i = *index;
+	unsigned int off = *offset;
 	unsigned int name_len;
 	const unsigned char *name;
 
-	for (i = 0, off = 0; len && i < kallsyms_num_syms; i++) {
+	for (; len && i < kallsyms_num_syms; i++) {
 		/*
 		 * For each symbol entry, the storage format is:
 		 *  ----------------------------
@@ -290,6 +293,10 @@ static int kallsyms_lookup_compressed_name(unsigned char *namebuf, int len,
 			continue;
 
 		if (!memcmp(name, namebuf, len)) {
+			/* Prepare for the next iteration */
+			*index = i + 1;
+			*offset = off;
+
 			*addr = kallsyms_sym_address(i);
 			return 0;
 		}
@@ -298,6 +305,14 @@ static int kallsyms_lookup_compressed_name(unsigned char *namebuf, int len,
 	return -ENOENT;
 }
 
+static int kallsyms_lookup_compressed_name(unsigned char *namebuf, int len,
+					   unsigned long *addr)
+{
+	unsigned int i = 0, off = 0;
+
+	return __kallsyms_lookup_compressed_name(namebuf, len, &i, &off, addr);
+}
+
 /* Lookup the address for this symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name)
 {
@@ -348,6 +363,27 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
 	return 0;
 }
 
+int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long),
+				  const char *name, void *data)
+{
+	int ret, len;
+	unsigned long addr;
+	unsigned int i = 0, off = 0;
+	char namebuf[KSYM_NAME_LEN];
+
+	len = kallsyms_compress_symbol_name(name, namebuf, ARRAY_SIZE(namebuf));
+	do {
+		ret = __kallsyms_lookup_compressed_name(namebuf, len, &i, &off, &addr);
+		if (ret)
+			return 0;	/* end of lookup */
+
+		ret = fn(data, addr);
+		cond_resched();
+	} while (!ret);
+
+	return ret;
+}
+
 static unsigned long get_symbol_pos(unsigned long addr,
 				    unsigned long *symbolsize,
 				    unsigned long *offset)
-- 
2.25.1