Merge branch 'bc/racy-4gb-files'

The index file has room only for lower 32-bit of the file size in
the cached stat information, which means cached stat information
will have 0 in its sd_size member for a file whose size is multiple
of 4GiB.  This is mistaken for a racily clean path.  Avoid it by
storing a bogus sd_size value instead for such files.

* bc/racy-4gb-files:
  Prevent git from rehashing 4GiB files
  t: add a test helper to truncate files

Author: gitster

Makefile

@@ -852,6 +852,7 @@ TEST_BUILTINS_OBJS += test-submodule-nested-repo-config.o
 TEST_BUILTINS_OBJS += test-submodule.o
 TEST_BUILTINS_OBJS += test-subprocess.o
 TEST_BUILTINS_OBJS += test-trace2.o
+TEST_BUILTINS_OBJS += test-truncate.o
 TEST_BUILTINS_OBJS += test-urlmatch-normalization.o
 TEST_BUILTINS_OBJS += test-userdiff.o
 TEST_BUILTINS_OBJS += test-wildmatch.o

statinfo.c

@@ -2,6 +2,22 @@
 #include "environment.h"
 #include "statinfo.h"
 
+/*
+ * Munge st_size into an unsigned int.
+ */
+static unsigned int munge_st_size(off_t st_size) {
+	unsigned int sd_size = st_size;
+
+	/*
+	 * If the file is an exact multiple of 4 GiB, modify the value so it
+	 * doesn't get marked as racily clean (zero).
+	 */
+	if (!sd_size && st_size)
+		return 0x80000000;
+	else
+		return sd_size;
+}
+
 void fill_stat_data(struct stat_data *sd, struct stat *st)
 {
 	sd->sd_ctime.sec = (unsigned int)st->st_ctime;
@@ -12,7 +28,7 @@ void fill_stat_data(struct stat_data *sd, struct stat *st)
 	sd->sd_ino = st->st_ino;
 	sd->sd_uid = st->st_uid;
 	sd->sd_gid = st->st_gid;
-	sd->sd_size = st->st_size;
+	sd->sd_size = munge_st_size(st->st_size);
 }
 
 int match_stat_data(const struct stat_data *sd, struct stat *st)
@@ -51,7 +67,7 @@ int match_stat_data(const struct stat_data *sd, struct stat *st)
 			changed |= INODE_CHANGED;
 #endif
 
-	if (sd->sd_size != (unsigned int) st->st_size)
+	if (sd->sd_size != munge_st_size(st->st_size))
 		changed |= DATA_CHANGED;
 
 	return changed;

t/helper/test-tool.c

@@ -86,6 +86,7 @@ static struct test_cmd cmds[] = {
 	{ "submodule-nested-repo-config", cmd__submodule_nested_repo_config },
 	{ "subprocess", cmd__subprocess },
 	{ "trace2", cmd__trace2 },
+	{ "truncate", cmd__truncate },
 	{ "userdiff", cmd__userdiff },
 	{ "urlmatch-normalization", cmd__urlmatch_normalization },
 	{ "xml-encode", cmd__xml_encode },

t/helper/test-tool.h

@@ -79,6 +79,7 @@ int cmd__submodule_config(int argc, const char **argv);
 int cmd__submodule_nested_repo_config(int argc, const char **argv);
 int cmd__subprocess(int argc, const char **argv);
 int cmd__trace2(int argc, const char **argv);
+int cmd__truncate(int argc, const char **argv);
 int cmd__userdiff(int argc, const char **argv);
 int cmd__urlmatch_normalization(int argc, const char **argv);
 int cmd__xml_encode(int argc, const char **argv);

t/helper/test-truncate.c

@@ -0,0 +1,25 @@
+#include "test-tool.h"
+#include "git-compat-util.h"
+
+/*
+ * Truncate a file to the given size.
+ */
+int cmd__truncate(int argc, const char **argv)
+{
+	char *p = NULL;
+	uintmax_t sz = 0;
+	int fd = -1;
+
+	if (argc != 3)
+		die("expected filename and size");
+
+	sz = strtoumax(argv[2], &p, 0);
+	if (*p)
+		die("invalid size");
+
+	fd = xopen(argv[1], O_WRONLY | O_CREAT, 0600);
+
+	if (ftruncate(fd, (off_t) sz) < 0)
+		die_errno("failed to truncate file");
+	return 0;
+}

t/t7508-status.sh

@@ -1745,4 +1745,20 @@ test_expect_success 'slow status advice when core.untrackedCache true, and fsmon
 	)
 '
 
+test_expect_success EXPENSIVE 'status does not re-read unchanged 4 or 8 GiB file' '
+	(
+		mkdir large-file &&
+		cd large-file &&
+		# Files are 2 GiB, 4 GiB, and 8 GiB sparse files.
+		test-tool truncate file-a 0x080000000 &&
+		test-tool truncate file-b 0x100000000 &&
+		test-tool truncate file-c 0x200000000 &&
+		# This will be slow.
+		git add file-a file-b file-c &&
+		git commit -m "add large files" &&
+		git diff-index HEAD file-a file-b file-c >actual &&
+		test_must_be_empty actual
+	)
+'
+
 test_done