[PATCH 5/7] pack-objects: use size_t for in-core object sizes

["Johannes Schindelin via GitGitGadget" <gitgitgadget@gmail.com>]

From: Johannes Schindelin <johannes.schindelin@gmx.de>

`pack-objects` stores per-entry object sizes in either the 31-bit
`size_` member of the `struct object_entry` or, when the value does not
fit, the `pack->delta_size[]` spill array.  The accessors (`oe_size`,
`oe_delta_size`, `oe_get_size_slow`, `oe_size_*_than`) and the setters
(`oe_set_size`, `oe_set_delta_size`) used `unsigned long` for the spill
type, which on Windows means the spill silently caps at 4 GiB per entry.
That is what made `upload-pack` die with "object too large to read on
this platform" when serving the >4 GiB blob in `t5608` tests 5 and 6
when run with `GIT_TEST_CLONE_2GB`.

Widen them all to `size_t` (including `pack->delta_size`) and drop the
three `cast_size_t_to_ulong()` calls in `check_object()` that guarded
`in_pack_size`.  The two `SET_SIZE(entry, canonical_size)` calls in the
same function stay cast-free as before, since `canonical_size` is still
`unsigned long` until a later commit widens `object_info::sizep`.

Assisted-by: Opus 4.7
Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
---
 builtin/pack-objects.c | 35 ++++++++++++++++++-----------------
 pack-objects.h         |  2 +-
 2 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 975f04d699..bb372d0b03 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -66,8 +66,8 @@ static inline struct object_entry *oe_delta(
 		return &pack->objects[e->delta_idx - 1];
 }
 
-static inline unsigned long oe_delta_size(struct packing_data *pack,
-					  const struct object_entry *e)
+static inline size_t oe_delta_size(struct packing_data *pack,
+				   const struct object_entry *e)
 {
 	if (e->delta_size_valid)
 		return e->delta_size_;
@@ -83,11 +83,11 @@ static inline unsigned long oe_delta_size(struct packing_data *pack,
 	return pack->delta_size[e - pack->objects];
 }
 
-unsigned long oe_get_size_slow(struct packing_data *pack,
-			       const struct object_entry *e);
+size_t oe_get_size_slow(struct packing_data *pack,
+			const struct object_entry *e);
 
-static inline unsigned long oe_size(struct packing_data *pack,
-				    const struct object_entry *e)
+static inline size_t oe_size(struct packing_data *pack,
+			     const struct object_entry *e)
 {
 	if (e->size_valid)
 		return e->size_;
@@ -145,7 +145,7 @@ static inline void oe_set_delta_sibling(struct packing_data *pack,
 
 static inline void oe_set_size(struct packing_data *pack,
 			       struct object_entry *e,
-			       unsigned long size)
+			       size_t size)
 {
 	if (size < pack->oe_size_limit) {
 		e->size_ = size;
@@ -159,7 +159,7 @@ static inline void oe_set_size(struct packing_data *pack,
 
 static inline void oe_set_delta_size(struct packing_data *pack,
 				     struct object_entry *e,
-				     unsigned long size)
+				     size_t size)
 {
 	if (size < pack->oe_delta_size_limit) {
 		e->delta_size_ = size;
@@ -496,7 +496,7 @@ static void copy_pack_data(struct hashfile *f,
 
 static inline int oe_size_greater_than(struct packing_data *pack,
 				       const struct object_entry *lhs,
-				       unsigned long rhs)
+				       size_t rhs)
 {
 	if (lhs->size_valid)
 		return lhs->size_ > rhs;
@@ -2277,7 +2277,7 @@ static void check_object(struct object_entry *entry, uint32_t object_index)
 		default:
 			/* Not a delta hence we've already got all we need. */
 			oe_set_type(entry, entry->in_pack_type);
-			SET_SIZE(entry, cast_size_t_to_ulong(in_pack_size));
+			SET_SIZE(entry, in_pack_size);
 			entry->in_pack_header_size = used;
 			if (oe_type(entry) < OBJ_COMMIT || oe_type(entry) > OBJ_BLOB)
 				goto give_up;
@@ -2331,8 +2331,8 @@ static void check_object(struct object_entry *entry, uint32_t object_index)
 		if (have_base &&
 		    can_reuse_delta(&base_ref, entry, &base_entry)) {
 			oe_set_type(entry, entry->in_pack_type);
-			SET_SIZE(entry, cast_size_t_to_ulong(in_pack_size)); /* delta size */
-			SET_DELTA_SIZE(entry, cast_size_t_to_ulong(in_pack_size));
+			SET_SIZE(entry, in_pack_size); /* delta size */
+			SET_DELTA_SIZE(entry, in_pack_size);
 
 			if (base_entry) {
 				SET_DELTA(entry, base_entry);
@@ -2355,7 +2355,8 @@ static void check_object(struct object_entry *entry, uint32_t object_index)
 			 * object size from the delta header.
 			 */
 			delta_pos = entry->in_pack_offset + entry->in_pack_header_size;
-			canonical_size = get_size_from_delta(p, &w_curs, delta_pos);
+			canonical_size = get_size_from_delta(p, &w_curs,
+							     delta_pos);
 			if (canonical_size == 0)
 				goto give_up;
 			SET_SIZE(entry, canonical_size);
@@ -2711,7 +2712,7 @@ static pthread_mutex_t progress_mutex;
 
 static inline int oe_size_less_than(struct packing_data *pack,
 				    const struct object_entry *lhs,
-				    unsigned long rhs)
+				    size_t rhs)
 {
 	if (lhs->size_valid)
 		return lhs->size_ < rhs;
@@ -2734,8 +2735,8 @@ static inline void oe_set_tree_depth(struct packing_data *pack,
  * reconstruction (so non-deltas are true object sizes, but deltas
  * return the size of the delta data).
  */
-unsigned long oe_get_size_slow(struct packing_data *pack,
-			       const struct object_entry *e)
+size_t oe_get_size_slow(struct packing_data *pack,
+			const struct object_entry *e)
 {
 	struct packed_git *p;
 	struct pack_window *w_curs;
@@ -2769,7 +2770,7 @@ unsigned long oe_get_size_slow(struct packing_data *pack,
 
 	unuse_pack(&w_curs);
 	packing_data_unlock(&to_pack);
-	return cast_size_t_to_ulong(size);
+	return size;
 }
 
 static int try_delta(struct unpacked *trg, struct unpacked *src,
diff --git a/pack-objects.h b/pack-objects.h
index 83299d4732..e97e84ddcb 100644
--- a/pack-objects.h
+++ b/pack-objects.h
@@ -141,7 +141,7 @@ struct packing_data {
 	uint32_t index_size;
 
 	unsigned int *in_pack_pos;
-	unsigned long *delta_size;
+	size_t *delta_size;
 
 	/*
 	 * Only one of these can be non-NULL and they have different
-- 
gitgitgadget