Merge branch 'js/regexec-buf'

Some codepaths in "git diff" used regexec(3) on a buffer that was
mmap(2)ed, which may not have a terminating NUL, leading to a read
beyond the end of the mapped region.  This was fixed by introducing
a regexec_buf() helper that takes a <ptr,len> pair with REG_STARTEND
extension.

* js/regexec-buf:
  regex: use regexec_buf()
  regex: add regexec_buf() that can work on a non NUL-terminated string
  regex: -G<pattern> feeds a non NUL-terminated string to regexec() and fails

7 files changed, 53 insertions, 33 deletions

diff --git a/Makefile b/Makefile
index e8b060a..1aad150 100644
--- a/Makefile
+++ b/Makefile
@@ -301,7 +301,8 @@ all::
 # crashes due to allocation and free working on different 'heaps'.
 # It's defined automatically if USE_NED_ALLOCATOR is set.
 #
-# Define NO_REGEX if you have no or inferior regex support in your C library.
+# Define NO_REGEX if your C library lacks regex support with REG_STARTEND
+# feature.
 #
 # Define HAVE_DEV_TTY if your system can open /dev/tty to interact with the
 # user.
diff --git a/diff.c b/diff.c
index 2cc3a2e..a178ed3 100644
--- a/diff.c
+++ b/diff.c
@@ -971,7 +971,8 @@ static int find_word_boundaries(mmfile_t *buffer, regex_t *word_regex,
 {
 	if (word_regex && *begin < buffer->size) {
 		regmatch_t match[1];
-		if (!regexec(word_regex, buffer->ptr + *begin, 1, match, 0)) {
+		if (!regexec_buf(word_regex, buffer->ptr + *begin,
+				 buffer->size - *begin, 1, match, 0)) {
 			char *p = memchr(buffer->ptr + *begin + match[0].rm_so,
 					'\n', match[0].rm_eo - match[0].rm_so);
 			*end = p ? p - buffer->ptr : match[0].rm_eo + *begin;
diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
index 55067ca..9795ca1 100644
--- a/diffcore-pickaxe.c
+++ b/diffcore-pickaxe.c
@@ -23,7 +23,6 @@ static void diffgrep_consume(void *priv, char *line, unsigned long len)
 {
 	struct diffgrep_cb *data = priv;
 	regmatch_t regmatch;
-	int hold;
 
 	if (line[0] != '+' && line[0] != '-')
 		return;
@@ -33,11 +32,8 @@ static void diffgrep_consume(void *priv, char *line, unsigned long len)
 		 * caller early.
 		 */
 		return;
-	/* Yuck -- line ought to be "const char *"! */
-	hold = line[len];
-	line[len] = '\0';
-	data->hit = !regexec(data->regexp, line + 1, 1, &regmatch, 0);
-	line[len] = hold;
+	data->hit = !regexec_buf(data->regexp, line + 1, len - 1, 1,
+				 &regmatch, 0);
 }
 
 static int diff_grep(mmfile_t *one, mmfile_t *two,
@@ -50,9 +46,11 @@ static int diff_grep(mmfile_t *one, mmfile_t *two,
 	xdemitconf_t xecfg;
 
 	if (!one)
-		return !regexec(regexp, two->ptr, 1, &regmatch, 0);
+		return !regexec_buf(regexp, two->ptr, two->size,
+				    1, &regmatch, 0);
 	if (!two)
-		return !regexec(regexp, one->ptr, 1, &regmatch, 0);
+		return !regexec_buf(regexp, one->ptr, one->size,
+				    1, &regmatch, 0);
 
 	/*
 	 * We have both sides; need to run textual diff and see if
@@ -83,8 +81,8 @@ static unsigned int contains(mmfile_t *mf, regex_t *regexp, kwset_t kws)
 		regmatch_t regmatch;
 		int flags = 0;
 
-		assert(data[sz] == '\0');
-		while (*data && !regexec(regexp, data, 1, &regmatch, flags)) {
+		while (*data &&
+		       !regexec_buf(regexp, data, sz, 1, &regmatch, flags)) {
 			flags |= REG_NOTBOL;
 			data += regmatch.rm_eo;
 			if (*data && regmatch.rm_so == regmatch.rm_eo)
diff --git a/git-compat-util.h b/git-compat-util.h
index 37cce07..8aab0c3 100644
--- a/git-compat-util.h
+++ b/git-compat-util.h
@@ -977,6 +977,19 @@ void git_qsort(void *base, size_t nmemb, size_t size,
 #define qsort git_qsort
 #endif
 
+#ifndef REG_STARTEND
+#error "Git requires REG_STARTEND support. Compile with NO_REGEX=NeedsStartEnd"
+#endif
+
+static inline int regexec_buf(const regex_t *preg, const char *buf, size_t size,
+			      size_t nmatch, regmatch_t pmatch[], int eflags)
+{
+	assert(nmatch > 0 && pmatch);
+	pmatch[0].rm_so = 0;
+	pmatch[0].rm_eo = size;
+	return regexec(preg, buf, nmatch, pmatch, eflags | REG_STARTEND);
+}
+
 #ifndef DIR_HAS_BSD_GROUP_SEMANTICS
 # define FORCE_DIR_SET_GID S_ISGID
 #else
diff --git a/grep.c b/grep.c
index d7d00b8..1194d35 100644
--- a/grep.c
+++ b/grep.c
@@ -898,17 +898,6 @@ static int fixmatch(struct grep_pat *p, char *line, char *eol,
 	}
 }
 
-static int regmatch(const regex_t *preg, char *line, char *eol,
-		    regmatch_t *match, int eflags)
-{
-#ifdef REG_STARTEND
-	match->rm_so = 0;
-	match->rm_eo = eol - line;
-	eflags |= REG_STARTEND;
-#endif
-	return regexec(preg, line, 1, match, eflags);
-}
-
 static int patmatch(struct grep_pat *p, char *line, char *eol,
 		    regmatch_t *match, int eflags)
 {
@@ -919,7 +908,8 @@ static int patmatch(struct grep_pat *p, char *line, char *eol,
 	else if (p->pcre_regexp)
 		hit = !pcrematch(p, line, eol, match, eflags);
 	else
-		hit = !regmatch(&p->regexp, line, eol, match, eflags);
+		hit = !regexec_buf(&p->regexp, line, eol - line, 1, match,
+				   eflags);
 
 	return hit;
 }
diff --git a/t/t4062-diff-pickaxe.sh b/t/t4062-diff-pickaxe.sh
new file mode 100755
index 0000000..f0bf50b
--- /dev/null
+++ b/t/t4062-diff-pickaxe.sh
@@ -0,0 +1,22 @@
+#!/bin/sh
+#
+# Copyright (c) 2016 Johannes Schindelin
+#
+
+test_description='Pickaxe options'
+
+. ./test-lib.sh
+
+test_expect_success setup '
+	test_commit initial &&
+	printf "%04096d" 0 >4096-zeroes.txt &&
+	git add 4096-zeroes.txt &&
+	test_tick &&
+	git commit -m "A 4k file"
+'
+test_expect_success '-G matches' '
+	git diff --name-only -G "^0{4096}$" HEAD^ >out &&
+	test 4096-zeroes.txt = "$(cat out)"
+'
+
+test_done
diff --git a/xdiff-interface.c b/xdiff-interface.c
index 3bfc69c..060038c 100644
--- a/xdiff-interface.c
+++ b/xdiff-interface.c
@@ -214,11 +214,10 @@ struct ff_regs {
 static long ff_regexp(const char *line, long len,
 		char *buffer, long buffer_size, void *priv)
 {
-	char *line_buffer;
 	struct ff_regs *regs = priv;
 	regmatch_t pmatch[2];
 	int i;
-	int result = -1;
+	int result;
 
 	/* Exclude terminating newline (and cr) from matching */
 	if (len > 0 && line[len-1] == '\n') {
@@ -228,18 +227,16 @@ static long ff_regexp(const char *line, long len,
 			len--;
 	}
 
-	line_buffer = xstrndup(line, len); /* make NUL terminated */
-
 	for (i = 0; i < regs->nr; i++) {
 		struct ff_reg *reg = regs->array + i;
-		if (!regexec(&reg->re, line_buffer, 2, pmatch, 0)) {
+		if (!regexec_buf(&reg->re, line, len, 2, pmatch, 0)) {
 			if (reg->negate)
-				goto fail;
+				return -1;
 			break;
 		}
 	}
 	if (regs->nr <= i)
-		goto fail;
+		return -1;
 	i = pmatch[1].rm_so >= 0 ? 1 : 0;
 	line += pmatch[i].rm_so;
 	result = pmatch[i].rm_eo - pmatch[i].rm_so;
@@ -248,8 +245,6 @@ static long ff_regexp(const char *line, long len,
 	while (result > 0 && (isspace(line[result - 1])))
 		result--;
 	memcpy(buffer, line, result);
- fail:
-	free(line_buffer);
 	return result;
 }