[PATCH 2/4] fsck: use size_t for the size of objects to check

WARM1d

From: Elia Pinto <hidden>
Date: 2026-10-31 11:10:20
Subsystem: the rest · Maintainer: Linus Torvalds

fsck functions such as fsck_object() and fsck_buffer() take the object
size as an "unsigned long", while some callers pass a size_t. On
platforms where "long" is 32 bits, this truncates the size for objects
of 4GiB or more.

When checking large objects on those platforms, fsck inspects only a
prefix of the buffer.

Use size_t for the size parameter across the fsck functions and internal
helpers, including the loop index in verify_headers().

Some callers and pack verification paths still pass "unsigned long" to
fsck_object(), and fsck_tree() passes the size to tree-walk routines;
those will be updated separately.

Triggering this requires processing 4GiB or more of input on a platform
where "long" is 32 bits, so no test is added.

Signed-off-by: Elia Pinto <redacted>
---
 fsck.c | 18 +++++++++---------
 fsck.h |  6 +++---
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/fsck.c b/fsck.c
index 94c8651c7d..7b0e9a5892 100644
--- a/fsck.c
+++ b/fsck.c

@@ -614,7 +614,7 @@ static int verify_ordered(unsigned mode1, const char *name1,
 }
 
 static int fsck_tree(const struct object_id *tree_oid,
-		     const char *buffer, unsigned long size,
+		     const char *buffer, size_t size,
 		     struct fsck_options *options)
 {
 	int retval = 0;

@@ -826,12 +826,12 @@ static int fsck_tree(const struct object_id *tree_oid,
  *     case hit the newline we found here as the end-of-header. This makes it
  *     OK for them to use helpers like parse_oid_hex(), or even skip_prefix().
  */
-static int verify_headers(const void *data, unsigned long size,
+static int verify_headers(const void *data, size_t size,
 			  const struct object_id *oid, enum object_type type,
 			  struct fsck_options *options)
 {
 	const char *buffer = (const char *)data;
-	unsigned long i;
+	size_t i;
 
 	for (i = 0; i < size; i++) {
 		switch (buffer[i]) {

@@ -948,7 +948,7 @@ static int fsck_ident(const char **ident, const char *ident_end,
 }
 
 static int fsck_commit(const struct object_id *oid,
-		       const char *buffer, unsigned long size,
+		       const char *buffer, size_t size,
 		       struct fsck_options *options)
 {
 	struct object_id tree_oid, parent_oid;

@@ -1010,7 +1010,7 @@ static int fsck_commit(const struct object_id *oid,
 }
 
 static int fsck_tag(const struct object_id *oid, const char *buffer,
-		    unsigned long size, struct fsck_options *options)
+		    size_t size, struct fsck_options *options)
 {
 	struct object_id tagged_oid;
 	int tagged_type;

@@ -1019,7 +1019,7 @@ static int fsck_tag(const struct object_id *oid, const char *buffer,
 }
 
 int fsck_tag_standalone(const struct object_id *oid, const char *buffer,
-			unsigned long size, struct fsck_options *options,
+			size_t size, struct fsck_options *options,
 			struct object_id *tagged_oid,
 			int *tagged_type)
 {

@@ -1182,7 +1182,7 @@ static int fsck_gitmodules_fn(const char *var, const char *value,
 }
 
 static int fsck_blob(const struct object_id *oid, const char *buf,
-		     unsigned long size, struct fsck_options *options)
+		     size_t size, struct fsck_options *options)
 {
 	int ret = 0;

@@ -1251,7 +1251,7 @@ static int fsck_blob(const struct object_id *oid, const char *buf,
 	return ret;
 }
 
-int fsck_object(struct object *obj, void *data, unsigned long size,
+int fsck_object(struct object *obj, void *data, size_t size,
 	struct fsck_options *options)
 {
 	if (!obj)

@@ -1261,7 +1261,7 @@ int fsck_object(struct object *obj, void *data, unsigned long size,
 }
 
 int fsck_buffer(const struct object_id *oid, enum object_type type,
-		const void *data, unsigned long size,
+		const void *data, size_t size,
 		struct fsck_options *options)
 {
 	if (type == OBJ_BLOB)

diff --git a/fsck.h b/fsck.h
index e77935c8a9..2a075a5572 100644
--- a/fsck.h
+++ b/fsck.h

@@ -196,7 +196,7 @@ int fsck_walk(struct object *obj, void *data, struct fsck_options *options);
  * Blob objects my pass a NULL data pointer, which indicates they are too large
  * to fit in memory. All other types must pass a real buffer.
  */
-int fsck_object(struct object *obj, void *data, unsigned long size,
+int fsck_object(struct object *obj, void *data, size_t size,
 	struct fsck_options *options);
 
 /*

@@ -204,7 +204,7 @@ int fsck_object(struct object *obj, void *data, unsigned long size,
  * struct.
  */
 int fsck_buffer(const struct object_id *oid, enum object_type,
-		const void *data, unsigned long size,
+		const void *data, size_t size,
 		struct fsck_options *options);
 
 /*

@@ -212,7 +212,7 @@ int fsck_buffer(const struct object_id *oid, enum object_type,
  * exposed fsck_object() internals for git-mktag(1).
  */
 int fsck_tag_standalone(const struct object_id *oid, const char *buffer,
-			unsigned long size, struct fsck_options *options,
+			size_t size, struct fsck_options *options,
 			struct object_id *tagged_oid,
 			int *tag_type);

-- 
2.53.0

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help