From b956cd500a48da9accf5ea24ce7d4419e7c8824b Mon Sep 17 00:00:00 2001
From: Jim Meyering <address@hidden>
Date: Sat, 14 Dec 2013 09:34:08 -0800
Subject: [PATCH] grep: handle lines longer than INT_MAX on more systems

When trying to exercize some long-line-handling code, I ran these
commands:
  $ dd bs=1 seek=2G of=big < /dev/null; grep -l x big; echo $?
  grep: big: Invalid argument
  2
grep should not have issued that diagnostic, and it should
have exited with status 1, not 2.  What happened?
grep read the 2GiB of NULs, doubled its buffer size,
copied the 2GiB into the new 4GiB buffer, and proceeded
to call "read" with a byte-count argument of 2^32.
On at least Darwin 12.5.0, that makes read fail with EINVAL.
The solution is to use gnulib's safe_read wrapper.
* src/main.c: Include "safe-read.h"
(fillbuf): Use safe_read, rather than bare read.  The latter
cannot handle a read size of 2^32 on some systems.
* bootstrap.conf (gnulib_modules): Add safe-read.
* tests/long-line-vs-2GiB-read: New file.
* tests/Makefile.am (TESTS): Add it.
* NEWS (Bug fixes): Mention it.
---
 NEWS                         |  2 ++
 bootstrap.conf               |  1 +
 src/main.c                   |  3 ++-
 tests/Makefile.am            |  1 +
 tests/long-line-vs-2GiB-read | 22 ++++++++++++++++++++++
 5 files changed, 28 insertions(+), 1 deletion(-)
 create mode 100755 tests/long-line-vs-2GiB-read

diff --git a/NEWS b/NEWS
index e974f29..80a064b 100644
--- a/NEWS
+++ b/NEWS
@@ -20,6 +20,8 @@ GNU grep NEWS                                    -*- outline -*-
     printf '\x82'|LC_ALL=en_US.UTF-8 grep -P y
   Now grep handles arbitrary PCRE errors.  [bug introduced in grep-2.15]

+  Handle very long lines (2GiB and longer) on systems with a deficient
+  read system call.

 * Noteworthy changes in release 2.15 (2013-10-26) [stable]

diff --git a/bootstrap.conf b/bootstrap.conf
index 8f6f5a3..580f01c 100644
--- a/bootstrap.conf
+++ b/bootstrap.conf
@@ -68,6 +68,7 @@ quote
 readme-release
 realloc-gnu
 regex
+safe-read
 same-inode
 ssize_t
 stddef
diff --git a/src/main.c b/src/main.c
index 4cee6c2..1dfbcb6 100644
--- a/src/main.c
+++ b/src/main.c
@@ -44,6 +44,7 @@
 #include "progname.h"
 #include "propername.h"
 #include "quote.h"
+#include "safe-read.h"
 #include "version-etc.h"
 #include "xalloc.h"
 #include "xstrtol.h"
@@ -641,7 +642,7 @@ fillbuf (size_t save, struct stat const *st)
   readsize = buffer + bufalloc - readbuf;
   readsize -= readsize % pagesize;

-  fillsize = read (bufdesc, readbuf, readsize);
+  fillsize = safe_read (bufdesc, readbuf, readsize);
   if (fillsize < 0)
     fillsize = cc = 0;
   bufoffset += fillsize;
diff --git a/tests/Makefile.am b/tests/Makefile.am
index 76b8c52..72af155 100644
--- a/tests/Makefile.am
+++ b/tests/Makefile.am
@@ -71,6 +71,7 @@ TESTS =						\
   inconsistent-range				\
   invalid-multibyte-infloop			\
   khadafy					\
+  long-line-vs-2GiB-read			\
   max-count-vs-context				\
   multibyte-white-space				\
   empty-line-mb					\
diff --git a/tests/long-line-vs-2GiB-read b/tests/long-line-vs-2GiB-read
new file mode 100755
index 0000000..773c542
--- /dev/null
+++ b/tests/long-line-vs-2GiB-read
@@ -0,0 +1,22 @@
+#!/bin/sh
+# Ensure that grep can handle lines 2GiB long.
+# Before grep-2.16, a line of length 2^31 or greater would provoke
+# an "Invalid argument" (EINVAL) failure from the read syscall on
+# systems like OS/X 10.8.5.
+
+. "${srcdir=.}/init.sh"; path_prepend_ ../src
+
+# Searching 2GiB takes a while.
+expensive_
+
+echo big > exp || framework_failure_
+
+MiB=1048576
+dd bs=$MiB seek=2048 of=big < /dev/null || framework_failure_
+echo x >> big || framework_failure_
+grep -l x big > out 2> err || fail=1
+
+compare exp out || fail=1
+compare /dev/null err || fail=1
+
+Exit $fail
-- 
1.8.5.rc2.6.gc6f1b92