[RFC] fixdep: faster CONFIG_search

[Tom Rini]

This is a port of dee81e988674 from Linux ("fixdep: faster CONFIG_
search") and posted by itself for ease of review.

To quote the kernel changelog:
"Do you think kernel build is 100% dominated by gcc? You are wrong!
One small utility called "fixdep" consistently manages to sneak into
profile's first page (unless you have small monitor of course).

The choke point is this clever code:

	for (; m < end; m++) {
		if (*m == INT_CONF) { p = (char *) m  ; goto conf; }
		if (*m == INT_ONFI) { p = (char *) m-1; goto conf; }
		if (*m == INT_NFIG) { p = (char *) m-2; goto conf; }
		if (*m == INT_FIG_) { p = (char *) m-3; goto conf; }

4 branches per 4 characters is not fast.

Use strstr(3), so that SSE2 etc can be used.

With this patch, fixdep is so deep at the bottom, it is hard to find
it."

Cc: Masahiro Yamada <masahiroy at kernel.org>
Signed-off-by: Tom Rini <trini at konsulko.com>
---
As part of working to re-sync our kbuild logic I see that fixdep.c
wasn't updated as part of the general resync with v4.17.  As this
specific change required some thinking to adapt our logic that was added
in 8be60f06c258 I am posting this change stand-alone for review.
---
 scripts/basic/fixdep.c | 100 ++++++++++++++---------------------------
 1 file changed, 33 insertions(+), 67 deletions(-)

diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c
index da7fb2cd4dde..6ab1780e4c02 100644
--- a/scripts/basic/fixdep.c
+++ b/scripts/basic/fixdep.c
@@ -82,8 +82,7 @@
  * to date before even starting the recursive build, so it's too late
  * at this point anyway.
  *
- * The algorithm to grep for "CONFIG_..." is bit unusual, but should
- * be fast ;-) We don't even try to really parse the header files, but
+ * We don't even try to really parse the header files, but
  * merely grep, i.e. if CONFIG_FOO is mentioned in a comment, it will
  * be picked up as well. It's not a problem with respect to
  * correctness, since that can only give too many dependencies, thus
@@ -115,11 +114,6 @@
 #include <ctype.h>
 #include <arpa/inet.h>
 
-#define INT_CONF ntohl(0x434f4e46)
-#define INT_ONFI ntohl(0x4f4e4649)
-#define INT_NFIG ntohl(0x4e464947)
-#define INT_FIG_ ntohl(0x4649475f)
-
 char *target;
 char *depfile;
 char *cmdline;
@@ -217,38 +211,20 @@ static void use_config(const char *m, int slen)
 	printf(".h) \\\n");
 }
 
-static void parse_config_file(const char *map, size_t len)
+static void parse_config_file(const char *p)
 {
-	const int *end = (const int *) (map + len);
-	/* start at +1, so that p can never be < map */
-	const int *m   = (const int *) map + 1;
-	const char *p, *q;
+	const char *q, *r;
 	char tmp_buf[256] = "SPL_"; /* hack for U-Boot */
 
-	for (; m < end; m++) {
-		if (*m == INT_CONF) { p = (char *) m  ; goto conf; }
-		if (*m == INT_ONFI) { p = (char *) m-1; goto conf; }
-		if (*m == INT_NFIG) { p = (char *) m-2; goto conf; }
-		if (*m == INT_FIG_) { p = (char *) m-3; goto conf; }
-		continue;
-	conf:
-		if (p > map + len - 7)
-			continue;
-		if (memcmp(p, "CONFIG_", 7))
-			continue;
+	while ((p = strstr(p, "CONFIG_"))) {
 		p += 7;
-		for (q = p; q < map + len; q++) {
-			if (!(isalnum(*q) || *q == '_'))
-				goto found;
-		}
-		continue;
-
-	found:
-		if (!memcmp(q - 7, "_MODULE", 7))
-			q -= 7;
-		if (q - p < 0)
-			continue;
-
+		q = p;
+		while (*q && (isalnum(*q) || *q == '_'))
+			q++;
+		if (memcmp(q - 7, "_MODULE", 7) == 0)
+			r = q - 7;
+		else
+			r = q;
 		/*
 		 * U-Boot also handles
 		 *   CONFIG_IS_ENABLED(...)
@@ -261,21 +237,20 @@ static void parse_config_file(const char *map, size_t len)
 		    (q - p == 9 && !memcmp(p, "IS_MODULE(", 10)) ||
 		    (q - p == 3 && !memcmp(p, "VAL(", 4))) {
 			p = q + 1;
-			for (q = p; q < map + len; q++)
-				if (*q == ')')
-					goto found2;
-			continue;
-
-		found2:
-			if (is_spl_build) {
-				memcpy(tmp_buf + 4, p, q - p);
-				q = tmp_buf + 4 + (q - p);
+			while (*q && *q != ')')
+				q++;
+			r = q;
+			if (r > p && is_spl_build) {
+				memcpy(tmp_buf + 4, p, r - p);
+				r = tmp_buf + 4 + (r - p);
 				p = tmp_buf;
 			}
 		}
 		/* end U-Boot hack */
 
-		use_config(p, q - p);
+		if (r > p)
+			use_config(p, r - p);
+		p = q;
 	}
 }
 
@@ -295,7 +270,7 @@ static void do_config_file(const char *filename)
 {
 	struct stat st;
 	int fd;
-	void *map;
+	char *map;
 
 	fd = open(filename, O_RDONLY);
 	if (fd < 0) {
@@ -312,18 +287,23 @@ static void do_config_file(const char *filename)
 		close(fd);
 		return;
 	}
-	map = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
-	if ((long) map == -1) {
-		perror("fixdep: mmap");
+	map = malloc(st.st_size + 1);
+	if (!map) {
+		perror("fixdep: malloc");
 		close(fd);
 		return;
 	}
+	if (read(fd, map, st.st_size) != st.st_size) {
+		perror("fixdep: read");
+		close(fd);
+		return;
+	}
+	map[st.st_size] = '\0';
+	close(fd);
 
-	parse_config_file(map, st.st_size);
-
-	munmap(map, st.st_size);
+	parse_config_file(map);
 
-	close(fd);
+	free(map);
 }
 
 /*
@@ -447,22 +427,8 @@ static void print_deps(void)
 	close(fd);
 }
 
-static void traps(void)
-{
-	static char test[] __attribute__((aligned(sizeof(int)))) = "CONF";
-	int *p = (int *)test;
-
-	if (*p != INT_CONF) {
-		fprintf(stderr, "fixdep: sizeof(int) != 4 or wrong endianness? %#x\n",
-			*p);
-		exit(2);
-	}
-}
-
 int main(int argc, char *argv[])
 {
-	traps();
-
 	if (argc != 4)
 		usage();
 
-- 
2.17.1