From cd4f888d16fd96a527a2c78f5167e679517540d6 Mon Sep 17 00:00:00 2001 From: Philip Oakley Date: Fri, 12 Nov 2021 21:16:51 +0000 Subject: [PATCH] hash algorithms: use size_t for section lengths Continue walking the code path for the >4GB `hash-object --literally` test to the hash algorithm step for LLP64 systems. This patch lets the SHA1DC code use `size_t`, making it compatible with LLP64 data models (as used e.g. by Windows). The interested reader of this patch will note that we adjust the signature of the `git_SHA1DCUpdate()` function without updating _any_ call site. This certainly puzzled at least one reviewer already, so here is an explanation: This function is never called directly, but always via the macro `platform_SHA1_Update`, which is usually called via the macro `git_SHA1_Update`. However, we never call `git_SHA1_Update()` directly in `struct git_hash_algo`. Instead, we call `git_hash_sha1_update()`, which is defined thusly: static void git_hash_sha1_update(git_hash_ctx *ctx, const void *data, size_t len) { git_SHA1_Update(&ctx->sha1, data, len); } i.e. it contains an implicit downcast from `size_t` to `unsigned long` (before this here patch). With this patch, there is no downcast anymore. With this patch, finally, the t1007-hash-object.sh "files over 4GB hash literally" test case is fixed. Signed-off-by: Philip Oakley Signed-off-by: Johannes Schindelin --- object-file.c | 4 ++-- sha1dc_git.c | 3 +-- sha1dc_git.h | 2 +- t/t1007-hash-object.sh | 2 +- 4 files changed, 5 insertions(+), 6 deletions(-) diff --git a/object-file.c b/object-file.c index bd59413eb7..f6257741b9 100644 --- a/object-file.c +++ b/object-file.c @@ -1785,7 +1785,7 @@ void *read_object_with_reference(struct repository *r, } static void hash_object_body(const struct git_hash_algo *algo, git_hash_ctx *c, - const void *buf, unsigned long len, + const void *buf, size_t len, struct object_id *oid, char *hdr, size_t *hdrlen) { @@ -1805,7 +1805,7 @@ static void write_object_file_prepare(const struct git_hash_algo *algo, /* Generate the header */ *hdrlen = format_object_header(hdr, *hdrlen, type, len); - /* Sha1.. */ + /* Hash (function pointers) computation */ hash_object_body(algo, &c, buf, len, oid, hdr, hdrlen); } diff --git a/sha1dc_git.c b/sha1dc_git.c index 5c300e812e..65a6f1f2cd 100644 --- a/sha1dc_git.c +++ b/sha1dc_git.c @@ -25,10 +25,9 @@ void git_SHA1DCFinal(unsigned char hash[20], SHA1_CTX *ctx) /* * Same as SHA1DCUpdate, but adjust types to match git's usual interface. */ -void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *vdata, unsigned long len) +void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *vdata, size_t len) { const char *data = vdata; - /* We expect an unsigned long, but sha1dc only takes an int */ while (len > INT_MAX) { SHA1DCUpdate(ctx, data, INT_MAX); data += INT_MAX; diff --git a/sha1dc_git.h b/sha1dc_git.h index 41e1c3fd3f..847b38fb4b 100644 --- a/sha1dc_git.h +++ b/sha1dc_git.h @@ -15,7 +15,7 @@ void git_SHA1DCInit(SHA1_CTX *); #endif void git_SHA1DCFinal(unsigned char [20], SHA1_CTX *); -void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *data, unsigned long len); +void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *data, size_t len); #define platform_SHA_CTX SHA1_CTX #define platform_SHA1_Init git_SHA1DCInit diff --git a/t/t1007-hash-object.sh b/t/t1007-hash-object.sh index 428298fa29..b30fb1282a 100755 --- a/t/t1007-hash-object.sh +++ b/t/t1007-hash-object.sh @@ -252,7 +252,7 @@ test_expect_success '--literally with extra-long type' ' echo example | git hash-object -t $t --literally --stdin ' -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 hash literally' ' test-tool genzeros $((5*1024*1024*1024)) >big && test_oid large5GB >expect &&