bsdgrep: add BSD_GREP_FASTMATCH knob for built-in fastmatch

Bugs have been found in the fastmatch implementation as used in bsdgrep.
Some have been fixed (r316495) while fixes for others are in review
(D10098).

In comparison with the fastmatch implementation, Kyle Evans found that:

- regex(3)'s performance with literal expressions offers a speed
  improvement over fastmatch

- regex(3)'s performance, both with simple BREs and EREs, seems to be
  comparable

The regex implementation was imported in r226035, and the commit message
reports:

    This is a temporary solution until the whole regex library is
    not replaced so that BSD grep development can continue and the
    backported code gets some review and testing. This change only
    improves scalability slightly, there is no big performance boost
    yet but several minor bugs have been found and fixed.

Introduce a WITH_/WITHOUT_BSD_GREP_FASTMATCH knob to support testing
of both approaches.

PR:		175314, 194823
Submitted by:	Kyle Evans <kevans91 at ksu.edu>
Reviewed by:	bdrewery (in part)
Differential Revision:	https://reviews.freebsd.org/D10282

4 files changed, 34 insertions, 9 deletions

diff --git a/usr.bin/grep/Makefile b/usr.bin/grep/Makefile
index 7c676591f83b..c6b25f06182d 100644
--- a/usr.bin/grep/Makefile
+++ b/usr.bin/grep/Makefile
@@ -15,10 +15,14 @@ bsdgrep.1: grep.1
 .endif
 SRCS=	file.c grep.c queue.c util.c
 
-# Extra files ported backported form some regex improvements
+.if ${MK_BSD_GREP_FASTMATCH} == "yes"
+# Extra files ported backported for some regex improvements
 .PATH: ${.CURDIR}/regex
 SRCS+=	fastmatch.c hashtable.c tre-compile.c tre-fastmatch.c
 CFLAGS+=-I${.CURDIR}/regex
+.else
+CFLAGS+= -DWITHOUT_FASTMATCH
+.endif
 
 CFLAGS.gcc+= --param max-inline-insns-single=500
 
diff --git a/usr.bin/grep/grep.c b/usr.bin/grep/grep.c
index be0a7355c968..20aec53f59cc 100644
--- a/usr.bin/grep/grep.c
+++ b/usr.bin/grep/grep.c
@@ -49,7 +49,9 @@ __FBSDID("$FreeBSD$");
 #include <string.h>
 #include <unistd.h>
 
+#ifndef WITHOUT_FASTMATCH
 #include "fastmatch.h"
+#endif
 #include "grep.h"
 
 #ifndef WITHOUT_NLS
@@ -86,7 +88,9 @@ unsigned int	 patterns;
 static unsigned int pattern_sz;
 struct pat	*pattern;
 regex_t		*r_pattern;
+#ifndef WITHOUT_FASTMATCH
 fastmatch_t	*fg_pattern;
+#endif
 
 /* Filename exclusion/inclusion patterns */
 unsigned int	fpatterns, dpatterns;
@@ -715,20 +719,25 @@ main(int argc, char *argv[])
 		usage();
 	}
 
+#ifndef WITHOUT_FASTMATCH
 	fg_pattern = grep_calloc(patterns, sizeof(*fg_pattern));
+#endif
 	r_pattern = grep_calloc(patterns, sizeof(*r_pattern));
 
 	/* Check if cheating is allowed (always is for fgrep). */
 	for (i = 0; i < patterns; ++i) {
+#ifndef WITHOUT_FASTMATCH
+		/* Attempt compilation with fastmatch regex and fallback to
+		   regex(3) if it fails. */
 		if (fastncomp(&fg_pattern[i], pattern[i].pat,
-		    pattern[i].len, cflags) != 0) {
-			/* Fall back to full regex library */
-			c = regcomp(&r_pattern[i], pattern[i].pat, cflags);
-			if (c != 0) {
-				regerror(c, &r_pattern[i], re_error,
-				    RE_ERROR_BUF);
-				errx(2, "%s", re_error);
-			}
+		    pattern[i].len, cflags) == 0)
+			continue;
+#endif
+		c = regcomp(&r_pattern[i], pattern[i].pat, cflags);
+		if (c != 0) {
+			regerror(c, &r_pattern[i], re_error,
+			    RE_ERROR_BUF);
+			errx(2, "%s", re_error);
 		}
 	}
 
diff --git a/usr.bin/grep/grep.h b/usr.bin/grep/grep.h
index c82e6bb9cbc9..ea17af4099dd 100644
--- a/usr.bin/grep/grep.h
+++ b/usr.bin/grep/grep.h
@@ -36,7 +36,9 @@
 #include <stdio.h>
 #include <zlib.h>
 
+#ifndef WITHOUT_FASTMATCH
 #include "fastmatch.h"
+#endif
 
 #ifdef WITHOUT_NLS
 #define	getstr(n)	 errstr[n]
@@ -127,7 +129,9 @@ extern unsigned int dpatterns, fpatterns, patterns;
 extern struct pat *pattern;
 extern struct epat *dpattern, *fpattern;
 extern regex_t	*er_pattern, *r_pattern;
+#ifndef WITHOUT_FASTMATCH
 extern fastmatch_t *fg_pattern;
+#endif
 
 /* For regex errors  */
 #define	RE_ERROR_BUF	512
diff --git a/usr.bin/grep/util.c b/usr.bin/grep/util.c
index 285f88364d3f..8815d4f34227 100644
--- a/usr.bin/grep/util.c
+++ b/usr.bin/grep/util.c
@@ -49,7 +49,9 @@ __FBSDID("$FreeBSD$");
 #include <wchar.h>
 #include <wctype.h>
 
+#ifndef WITHOUT_FASTMATCH
 #include "fastmatch.h"
+#endif
 #include "grep.h"
 
 static int	 linesqueued;
@@ -317,10 +319,12 @@ procline(struct str *l, int nottext)
 		for (i = 0; i < patterns; i++) {
 			pmatch.rm_so = st;
 			pmatch.rm_eo = l->len;
+#ifndef WITHOUT_FASTMATCH
 			if (fg_pattern[i].pattern)
 				r = fastexec(&fg_pattern[i],
 				    l->dat, 1, &pmatch, leflags);
 			else
+#endif
 				r = regexec(&r_pattern[i], l->dat, 1,
 				    &pmatch, leflags);
 			r = (r == 0) ? 0 : REG_NOMATCH;
@@ -332,7 +336,11 @@ procline(struct str *l, int nottext)
 				    (size_t)pmatch.rm_eo != l->len)
 					r = REG_NOMATCH;
 			/* Check for whole word match */
+#ifndef WITHOUT_FASTMATCH
 			if (r == 0 && (wflag || fg_pattern[i].word)) {
+#else
+			if (r == 0 && wflag) {
+#endif
 				wchar_t wbegin, wend;
 
 				wbegin = wend = L' ';