[PATCH v2 15/18] varint: use explicit width for integers

From: Patrick Steinhardt via GitGitGadget <gitgitgadget@gmail.com>
Date: Sep 17, 2025, 01:16 UTC
Message-ID: <df837fdb4d399be1218a9a39eab47a85fa44e8d3.1758071798.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.2043.v2.git.git.1758071798.gitgitgadget@gmail.com>

From: Patrick Steinhardt <ps@pks.im>

The varint subsystem currently uses implcit widths for integers. On the one hand we use `uintmax_t` for the actual value. On the other hand, we use `int` for the length of the encoded varint.

Both of these have known maximum vaules, as we only support at most 16 bytes when encoding varints. Thus, we know that we won't ever exceed `uint64_t` for the actual value and `uint8_t` for the prefix length.

Refactor the code to use explicit widths. Besides making the logic platform-independent, it also makes our life a bit easier in the next commit, where we reimplement "varint.c" in Rust.

Suggested-by: Ezekiel Newren <ezekielnewren@gmail.com>
Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Ezekiel Newren <ezekielnewren@gmail.com>
---
 dir.c        | 18 ++++++++++--------
 read-cache.c |  6 ++++--
 varint.c     |  6 +++---
 varint.h     |  4 ++--
 4 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/dir.c b/dir.c
index dfb4d40103..b92a5d750e 100644
--- a/dir.c
+++ b/dir.c
@@ -3579,7 +3579,8 @@ static void write_one_dir(struct untracked_cache_dir *untracked,
 	struct stat_data stat_data;
 	struct strbuf *out = &wd->out;
 	unsigned char intbuf[16];
-	unsigned int intlen, value;
+	unsigned int value;
+	uint8_t intlen;
 	int i = wd->index++;
 
 	/*
@@ -3632,7 +3633,7 @@ void write_untracked_extension(struct strbuf *out, struct untracked_cache *untra
 	struct ondisk_untracked_cache *ouc;
 	struct write_data wd;
 	unsigned char varbuf[16];
-	int varint_len;
+	uint8_t varint_len;
 	const unsigned hashsz = the_hash_algo->rawsz;
 
 	CALLOC_ARRAY(ouc, 1);
@@ -3738,7 +3739,7 @@ static int read_one_dir(struct untracked_cache_dir **untracked_,
 	struct untracked_cache_dir ud, *untracked;
 	const unsigned char *data = rd->data, *end = rd->end;
 	const unsigned char *eos;
-	unsigned int value;
+	uint64_t value;
 	int i;
 
 	memset(&ud, 0, sizeof(ud));
@@ -3830,7 +3831,8 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long
 	struct read_data rd;
 	const unsigned char *next = data, *end = (const unsigned char *)data + sz;
 	const char *ident;
-	int ident_len;
+	uint64_t ident_len;
+	uint64_t varint_len;
 	ssize_t len;
 	const char *exclude_per_dir;
 	const unsigned hashsz = the_hash_algo->rawsz;
@@ -3867,8 +3869,8 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long
 	if (next >= end)
 		goto done2;
 
-	len = decode_varint(&next);
-	if (next > end || len == 0)
+	varint_len = decode_varint(&next);
+	if (next > end || varint_len == 0)
 		goto done2;
 
 	rd.valid      = ewah_new();
@@ -3877,9 +3879,9 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long
 	rd.data	      = next;
 	rd.end	      = end;
 	rd.index      = 0;
-	ALLOC_ARRAY(rd.ucd, len);
+	ALLOC_ARRAY(rd.ucd, varint_len);
 
-	if (read_one_dir(&uc->root, &rd) || rd.index != len)
+	if (read_one_dir(&uc->root, &rd) || rd.index != varint_len)
 		goto done;
 
 	next = rd.data;
diff --git a/read-cache.c b/read-cache.c
index 06ad74db22..41b44148b1 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1807,7 +1807,7 @@ static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
 
 	if (expand_name_field) {
 		const unsigned char *cp = (const unsigned char *)name;
-		size_t strip_len, previous_len;
+		uint64_t strip_len, previous_len;
 
 		/* If we're at the beginning of a block, ignore the previous name */
 		strip_len = decode_varint(&cp);
@@ -2655,8 +2655,10 @@ static int ce_write_entry(struct hashfile *f, struct cache_entry *ce,
 		hashwrite(f, ce->name, len);
 		hashwrite(f, padding, align_padding_size(size, len));
 	} else {
-		int common, to_remove, prefix_size;
+		int common, to_remove;
+		uint8_t prefix_size;
 		unsigned char to_remove_vi[16];
+
 		for (common = 0;
 		     (common < previous_name->len &&
 		      ce->name[common] &&
diff --git a/varint.c b/varint.c
index 409c4977a1..03cd54416b 100644
--- a/varint.c
+++ b/varint.c
@@ -1,11 +1,11 @@
 #include "git-compat-util.h"
 #include "varint.h"
 
-uintmax_t decode_varint(const unsigned char **bufp)
+uint64_t decode_varint(const unsigned char **bufp)
 {
 	const unsigned char *buf = *bufp;
 	unsigned char c = *buf++;
-	uintmax_t val = c & 127;
+	uint64_t val = c & 127;
 	while (c & 128) {
 		val += 1;
 		if (!val || MSB(val, 7))
@@ -17,7 +17,7 @@ uintmax_t decode_varint(const unsigned char **bufp)
 	return val;
 }
 
-int encode_varint(uintmax_t value, unsigned char *buf)
+uint8_t encode_varint(uint64_t value, unsigned char *buf)
 {
 	unsigned char varint[16];
 	unsigned pos = sizeof(varint) - 1;
diff --git a/varint.h b/varint.h
index f78bb0ca52..eb401935bd 100644
--- a/varint.h
+++ b/varint.h
@@ -1,7 +1,7 @@
 #ifndef VARINT_H
 #define VARINT_H
 
-int encode_varint(uintmax_t, unsigned char *);
-uintmax_t decode_varint(const unsigned char **);
+uint8_t encode_varint(uint64_t, unsigned char *);
+uint64_t decode_varint(const unsigned char **);
 
 #endif /* VARINT_H */

-- 
gitgitgadget