Thread (29 messages) flat view 29 messages, 4 authors, 2026-06-18
STALE86d

[PATCH 4/7] packfile: widen unpack_entry()'s size out-parameter to size_t

From: Johannes Schindelin via GitGitGadget <hidden>
Date: 2026-06-04 10:51:21
Subsystem: the rest · Maintainer: Linus Torvalds

From: Johannes Schindelin <redacted>

The topic `js/objects-larger-than-4gb-on-windows` widened the streaming,
index-pack and unpack-objects paths to `size_t` but deliberately stopped
at the in-memory `unpack_entry()` cascade, which still hands back the
unpacked size through `unsigned long *`.  On Windows that boundary
truncates above 4 GiB because that data type is only 32 bits wide on
that platform.

Widen the code path. Except `packed_object_info_with_index_pos()`: It
cannot yet pass `oi->sizep` directly because the field is still
`unsigned long *`; bridge it with a `size_t` temporary that narrows
back, and let a later commit drop the bridge once the field is wide
too. `gfi_unpack_entry()` keeps its narrow signature because fast-import
tracks sizes through `unsigned long` everywhere it crosses subsystem
boundaries, keeping its signature allows the scope of this commit to be
somewhat reasonable, still.

Assisted-by: Opus 4.7
Signed-off-by: Johannes Schindelin <redacted>
---
 builtin/fast-import.c |  7 ++++++-
 pack-check.c          |  5 ++---
 packfile.c            | 28 +++++++++++++++++-----------
 packfile.h            |  3 ++-
 4 files changed, 27 insertions(+), 16 deletions(-)
diff --git a/builtin/fast-import.c b/builtin/fast-import.c
index 82bc6dcc00..3dff898c43 100644
--- a/builtin/fast-import.c
+++ b/builtin/fast-import.c
@@ -1239,6 +1239,8 @@ static void *gfi_unpack_entry(
 	unsigned long *sizep)
 {
 	enum object_type type;
+	size_t size_st = 0;
+	void *data;
 	struct packed_git *p = all_packs[oe->pack_id];
 	if (p == pack_data && p->pack_size < (pack_size + the_hash_algo->rawsz)) {
 		/* The object is stored in the packfile we are writing to
@@ -1260,7 +1262,10 @@ static void *gfi_unpack_entry(
 		 */
 		p->pack_size = pack_size + the_hash_algo->rawsz;
 	}
-	return unpack_entry(the_repository, p, oe->idx.offset, &type, sizep);
+	data = unpack_entry(the_repository, p, oe->idx.offset, &type, &size_st);
+	if (sizep)
+		*sizep = cast_size_t_to_ulong(size_st);
+	return data;
 }
 
 static void load_tree(struct tree_entry *root)
diff --git a/pack-check.c b/pack-check.c
index 2792f34d25..5adfb3f272 100644
--- a/pack-check.c
+++ b/pack-check.c
@@ -143,9 +143,8 @@ static int verify_packfile(struct repository *r,
 			data = NULL;
 			data_valid = 0;
 		} else {
-			unsigned long sz;
-			data = unpack_entry(r, p, entries[i].offset, &type, &sz);
-			size = sz;
+			data = unpack_entry(r, p, entries[i].offset, &type,
+					    &size);
 			data_valid = 1;
 		}
 
diff --git a/packfile.c b/packfile.c
index e202f48837..dab0a9b16d 100644
--- a/packfile.c
+++ b/packfile.c
@@ -1454,7 +1454,7 @@ struct delta_base_cache_entry {
 	struct delta_base_cache_key key;
 	struct list_head lru;
 	void *data;
-	unsigned long size;
+	size_t size;
 	enum object_type type;
 };
 
@@ -1525,7 +1525,7 @@ static void detach_delta_base_cache_entry(struct delta_base_cache_entry *ent)
 }
 
 static void *cache_or_unpack_entry(struct repository *r, struct packed_git *p,
-				   off_t base_offset, unsigned long *base_size,
+				   off_t base_offset, size_t *base_size,
 				   enum object_type *type)
 {
 	struct delta_base_cache_entry *ent;
@@ -1558,8 +1558,8 @@ void clear_delta_base_cache(void)
 }
 
 static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
-				 void *base, unsigned long base_size,
-				 unsigned long delta_base_cache_limit,
+				 void *base, size_t base_size,
+				 size_t delta_base_cache_limit,
 				 enum object_type type)
 {
 	struct delta_base_cache_entry *ent;
@@ -1614,10 +1614,13 @@ static int packed_object_info_with_index_pos(struct packed_git *p, off_t obj_off
 	 * a "real" type later if the caller is interested.
 	 */
 	if (oi->contentp) {
-		*oi->contentp = cache_or_unpack_entry(p->repo, p, obj_offset, oi->sizep,
-						      &type);
+		size_t size_st = 0;
+		*oi->contentp = cache_or_unpack_entry(p->repo, p, obj_offset,
+						      &size_st, &type);
 		if (!*oi->contentp)
 			type = OBJ_BAD;
+		else if (oi->sizep)
+			*oi->sizep = cast_size_t_to_ulong(size_st);
 	} else if (oi->sizep || oi->typep || oi->delta_base_oid) {
 		type = unpack_object_header(p, &w_curs, &curpos, &size);
 	}
@@ -1735,7 +1738,7 @@ int packed_object_info(struct packed_git *p, off_t obj_offset,
 static void *unpack_compressed_entry(struct packed_git *p,
 				    struct pack_window **w_curs,
 				    off_t curpos,
-				    unsigned long size)
+				    size_t size)
 {
 	int st;
 	git_zstream stream;
@@ -1790,11 +1793,11 @@ int do_check_packed_object_crc;
 struct unpack_entry_stack_ent {
 	off_t obj_offset;
 	off_t curpos;
-	unsigned long size;
+	size_t size;
 };
 
 void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset,
-		   enum object_type *final_type, unsigned long *final_size)
+		   enum object_type *final_type, size_t *final_size)
 {
 	struct pack_window *w_curs = NULL;
 	off_t curpos = obj_offset;
@@ -1911,7 +1914,7 @@ void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset,
 		void *delta_data;
 		void *base = data;
 		void *external_base = NULL;
-		unsigned long delta_size, base_size = size;
+		size_t delta_size, base_size = size;
 		int i;
 		off_t base_obj_offset = obj_offset;
 
@@ -1928,6 +1931,7 @@ void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset,
 			struct object_id base_oid;
 			if (!(offset_to_pack_pos(p, obj_offset, &pos))) {
 				struct object_info oi = OBJECT_INFO_INIT;
+				unsigned long bsz_ul = 0;
 
 				nth_packed_object_id(&base_oid, p,
 						     pack_pos_to_index(p, pos));
@@ -1938,11 +1942,13 @@ void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset,
 				mark_bad_packed_object(p, &base_oid);
 
 				oi.typep = &type;
-				oi.sizep = &base_size;
+				oi.sizep = &bsz_ul;
 				oi.contentp = &base;
 				if (odb_read_object_info_extended(r->objects, &base_oid,
 								  &oi, 0) < 0)
 					base = NULL;
+				else
+					base_size = bsz_ul;
 
 				external_base = base;
 			}
diff --git a/packfile.h b/packfile.h
index 49d6bdecf6..0b5ae3f9fc 100644
--- a/packfile.h
+++ b/packfile.h
@@ -455,7 +455,8 @@ off_t nth_packed_object_offset(const struct packed_git *, uint32_t n);
 off_t find_pack_entry_one(const struct object_id *oid, struct packed_git *);
 
 int is_pack_valid(struct packed_git *);
-void *unpack_entry(struct repository *r, struct packed_git *, off_t, enum object_type *, unsigned long *);
+void *unpack_entry(struct repository *r, struct packed_git *, off_t,
+		   enum object_type *, size_t *);
 unsigned long unpack_object_header_buffer(const unsigned char *buf, unsigned long len, enum object_type *type, size_t *sizep);
 unsigned long get_size_from_delta(struct packed_git *, struct pack_window **, off_t);
 int unpack_object_header(struct packed_git *, struct pack_window **, off_t *, size_t *);
-- 
gitgitgadget
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help