From 3b2148e2997b381131bff3e262e5d3b4754fed50 Mon Sep 17 00:00:00 2001
From: thomas <thomas@FreeBSD.org>
Date: Thu, 18 Feb 2016 08:44:16 +0000
Subject: [PATCH] Reorganize the handling all-zeroes terminal block in sparse
 mode

The intent of the previous code in that case was to force
an explicit write, but the implementation was incorrect, and
as a result the write was never performed. This new implementation
instead uses ftruncate(2) to extend the file with a trailing hole.

Also introduce regression tests for these cases.

PR: 189284
(original PR whose fix introduced this bug)

PR: 207092

Differential Revision:	D5248
Reviewed by:	sobomax,kib
MFC after:	2 weeks
---
 bin/dd/Makefile       | 13 ++++++++++++-
 bin/dd/dd.c           | 36 +++++++++++++++++++++---------------
 bin/dd/dd.h           |  1 +
 bin/dd/gen.c          | 13 ++++++++++---
 bin/dd/ref.obs_zeroes |  3 +++
 5 files changed, 47 insertions(+), 19 deletions(-)
 create mode 100644 bin/dd/ref.obs_zeroes

diff --git a/bin/dd/Makefile b/bin/dd/Makefile
index 5f07dbc248ac..6b17d290c6ee 100644
--- a/bin/dd/Makefile
+++ b/bin/dd/Makefile
@@ -24,7 +24,18 @@ test: ${PROG} gen
 	    LC_ALL=en_US.US-ASCII hexdump -C | \
 	    diff -I FreeBSD - ${.CURDIR}/ref.${conv}
 .endfor
-	@rm -f gen
+	@${ECHO} "testing sparse file (obs zeroes)"
+	@./gen 189284 | ./dd ibs=16 obs=8 conv=sparse of=obs_zeroes 2> /dev/null
+	@hexdump -C obs_zeroes | diff -I FreeBSD - ${.CURDIR}/ref.obs_zeroes
+
+	@${ECHO} "testing spase file (all zeroes)"
+	@./dd if=/dev/zero of=1M_zeroes bs=1048576 count=1 2> /dev/null
+	@./dd if=1M_zeroes of=1M_zeroes.1 bs=1048576 conv=sparse 2> /dev/null
+	@./dd if=1M_zeroes of=1M_zeroes.2 bs=1048576 2> /dev/null
+	@diff 1M_zeroes 1M_zeroes.1
+	@diff 1M_zeroes 1M_zeroes.2
+
+	@rm -f gen 1M_zeroes* obs_zeroes
 
 .if ${MK_TESTS} != "no"
 SUBDIR+=	tests
diff --git a/bin/dd/dd.c b/bin/dd/dd.c
index 8ae11a7d1636..4c31a5e81260 100644
--- a/bin/dd/dd.c
+++ b/bin/dd/dd.c
@@ -77,7 +77,6 @@ STAT	st;			/* statistics */
 void	(*cfunc)(void);		/* conversion function */
 uintmax_t cpy_cnt;		/* # of blocks to copy */
 static off_t	pending = 0;	/* pending seek if sparse */
-static off_t	last_sp = 0;	/* size of last added sparse block */
 u_int	ddflags = 0;		/* conversion options */
 size_t	cbsz;			/* conversion block size */
 uintmax_t files_cnt = 1;	/* # of files to copy */
@@ -409,6 +408,15 @@ dd_close(void)
 	}
 	if (out.dbcnt || pending)
 		dd_out(1);
+
+	/*
+	 * If the file ends with a hole, ftruncate it to extend its size
+	 * up to the end of the hole (without having to write any data).
+	 */
+	if (out.seek_offset > 0 && (out.flags & ISTRUNC)) {
+		if (ftruncate(out.fd, out.seek_offset) == -1)
+			err(1, "truncating %s", out.name);
+	}
 }
 
 void
@@ -457,29 +465,27 @@ dd_out(int force)
 			}
 			if (sparse && !force) {
 				pending += cnt;
-				last_sp = cnt;
 				nw = cnt;
 			} else {
 				if (pending != 0) {
-					/* If forced to write, and we have no
-					 * data left, we need to write the last
-					 * sparse block explicitly.
+					/*
+					 * Seek past hole.  Note that we need to record the
+					 * reached offset, because we might have no more data
+					 * to write, in which case we'll need to call
+					 * ftruncate to extend the file size.
 					 */
-					if (force && cnt == 0) {
-						pending -= last_sp;
-						assert(outp == out.db);
-						memset(outp, 0, cnt);
-					}
-					if (lseek(out.fd, pending, SEEK_CUR) ==
-					    -1)
+					out.seek_offset = lseek(out.fd, pending, SEEK_CUR);
+					if (out.seek_offset == -1)
 						err(2, "%s: seek error creating sparse file",
 						    out.name);
-					pending = last_sp = 0;
+					pending = 0;
 				}
-				if (cnt)
+				if (cnt) {
 					nw = write(out.fd, outp, cnt);
-				else
+					out.seek_offset = 0;
+				} else {
 					return;
+				}
 			}
 
 			if (nw <= 0) {
diff --git a/bin/dd/dd.h b/bin/dd/dd.h
index a8b45e594776..196f804c2ebe 100644
--- a/bin/dd/dd.h
+++ b/bin/dd/dd.h
@@ -54,6 +54,7 @@ typedef struct {
 	const char	*name;		/* name */
 	int		fd;		/* file descriptor */
 	off_t		offset;		/* # of blocks to skip */
+	off_t		seek_offset;	/* offset of last seek past output hole */
 } IO;
 
 typedef struct {
diff --git a/bin/dd/gen.c b/bin/dd/gen.c
index 9c7571a9ab91..d53d8fb2b5ac 100644
--- a/bin/dd/gen.c
+++ b/bin/dd/gen.c
@@ -5,13 +5,20 @@
  */
 
 #include <stdio.h>
+#include <string.h>
 
 int
-main(int argc __unused, char **argv __unused)
+main(int argc, char **argv)
 {
 	int i;
 
-	for (i = 0; i < 256; i++)
-		putchar(i);
+	if (argc > 1 && !strcmp(argv[1], "189284")) {
+		fputs("ABCDEFGH", stdout);
+		for (i = 0; i < 8; i++)
+			putchar(0);
+	} else {
+		for (i = 0; i < 256; i++)
+			putchar(i);
+	}
 	return (0);
 }
diff --git a/bin/dd/ref.obs_zeroes b/bin/dd/ref.obs_zeroes
new file mode 100644
index 000000000000..473ff7cc4108
--- /dev/null
+++ b/bin/dd/ref.obs_zeroes
@@ -0,0 +1,3 @@
+$FreeBSD$
+00000000  41 42 43 44 45 46 47 48  00 00 00 00 00 00 00 00  |ABCDEFGH........|
+00000010