odb: teach read_blob_entry to use size_t

vtbassmatt · gitster · commit e9aa762cc72e · 2021-11-03T11:22:27.000-07:00
There is mixed use of size_t and unsigned long to deal with sizes in the
codebase. Recall that Windows defines unsigned long as 32 bits even on
64-bit platforms, meaning that converting size_t to unsigned long narrows
the range. This mostly doesn't cause a problem since Git rarely deals
with files larger than 2^32 bytes.

But adjunct systems such as Git LFS, which use smudge/clean filters to
keep huge files out of the repository, may have huge file contents passed
through some of the functions in entry.c and convert.c. On Windows, this
results in a truncated file being written to the workdir. I traced this to
one specific use of unsigned long in write_entry (and a similar instance
in write_pc_item_to_fd for parallel checkout). That appeared to be for
the call to read_blob_entry, which expects a pointer to unsigned long.

By altering the signature of read_blob_entry to expect a size_t,
write_entry can be switched to use size_t internally (which all of its
callers and most of its callees already used). To avoid touching dozens of
additional files, read_blob_entry uses a local unsigned long to call a
chain of functions which aren't prepared to accept size_t.

Helped-by: Johannes Schindelin &lt;johannes.schindelin@gmx.de&gt;
Signed-off-by: Matt Cooper &lt;vtbassmatt@gmail.com&gt;
Signed-off-by: Johannes Schindelin &lt;johannes.schindelin@gmx.de&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/entry.c b/entry.c
@@ -82,11 +82,13 @@ static int create_file(const char *path, unsigned int mode)
 	return open(path, O_WRONLY | O_CREAT | O_EXCL, mode);
 }
 
-void *read_blob_entry(const struct cache_entry *ce, unsigned long *size)
+void *read_blob_entry(const struct cache_entry *ce, size_t *size)
 {
 	enum object_type type;
-	void *blob_data = read_object_file(&ce->oid, &type, size);
+	unsigned long ul;
+	void *blob_data = read_object_file(&ce->oid, &type, &ul);
 
+	*size = ul;
 	if (blob_data) {
 		if (type == OBJ_BLOB)
 			return blob_data;
@@ -270,7 +272,7 @@ static int write_entry(struct cache_entry *ce, char *path, struct conv_attrs *ca
 	int fd, ret, fstat_done = 0;
 	char *new_blob;
 	struct strbuf buf = STRBUF_INIT;
-	unsigned long size;
+	size_t size;
 	ssize_t wrote;
 	size_t newsize = 0;
 	struct stat st;
diff --git a/entry.h b/entry.h
@@ -51,7 +51,7 @@ int finish_delayed_checkout(struct checkout *state, int *nr_checkouts);
  */
 void unlink_entry(const struct cache_entry *ce);
 
-void *read_blob_entry(const struct cache_entry *ce, unsigned long *size);
+void *read_blob_entry(const struct cache_entry *ce, size_t *size);
 int fstat_checkout_output(int fd, const struct checkout *state, struct stat *st);
 void update_ce_after_write(const struct checkout *state, struct cache_entry *ce,
 			   struct stat *st);
diff --git a/parallel-checkout.c b/parallel-checkout.c
@@ -261,7 +261,7 @@ static int write_pc_item_to_fd(struct parallel_checkout_item *pc_item, int fd,
 	struct stream_filter *filter;
 	struct strbuf buf = STRBUF_INIT;
 	char *blob;
-	unsigned long size;
+	size_t size;
 	ssize_t wrote;
 
 	/* Sanity check */
diff --git a/t/t1051-large-conversion.sh b/t/t1051-large-conversion.sh
@@ -85,7 +85,7 @@ test_expect_success 'ident converts on output' '
 
 # This smudge filter prepends 5GB of zeros to the file it checks out. This
 # ensures that smudging doesn't mangle large files on 64-bit Windows.
-test_expect_failure EXPENSIVE,SIZE_T_IS_64BIT,!LONG_IS_64BIT \
+test_expect_success EXPENSIVE,SIZE_T_IS_64BIT,!LONG_IS_64BIT \
 		'files over 4GB convert on output' '
 	test_commit test small "a small file" &&
 	small_size=$(test_file_size small) &&
