diff --git a/Makefile b/Makefile index 7344a7f725..2dde1fd2b8 100644 --- a/Makefile +++ b/Makefile @@ -521,6 +521,10 @@ include shared.mak # Define APPLE_COMMON_CRYPTO_SHA1 to use Apple's CommonCrypto for # SHA-1. # +# Define the same Makefile knobs as above, but suffixed with _UNSAFE to +# use the corresponding implementations for unsafe SHA-1 hashing for +# non-cryptographic purposes. +# # If don't enable any of the *_SHA1 settings in this section, Git will # default to its built-in sha1collisiondetection library, which is a # collision-detecting sha1 This is slower, but may detect attempted @@ -1997,6 +2001,27 @@ endif endif endif +ifdef OPENSSL_SHA1_UNSAFE +ifndef OPENSSL_SHA1 + EXTLIBS += $(LIB_4_CRYPTO) + BASIC_CFLAGS += -DSHA1_OPENSSL_UNSAFE +endif +else +ifdef BLK_SHA1_UNSAFE +ifndef BLK_SHA1 + LIB_OBJS += block-sha1/sha1.o + BASIC_CFLAGS += -DSHA1_BLK_UNSAFE +endif +else +ifdef APPLE_COMMON_CRYPTO_SHA1_UNSAFE +ifndef APPLE_COMMON_CRYPTO_SHA1 + COMPAT_CFLAGS += -DCOMMON_DIGEST_FOR_OPENSSL + BASIC_CFLAGS += -DSHA1_APPLE_UNSAFE +endif +endif +endif +endif + ifdef OPENSSL_SHA256 EXTLIBS += $(LIB_4_CRYPTO) BASIC_CFLAGS += -DSHA256_OPENSSL diff --git a/block-sha1/sha1.h b/block-sha1/sha1.h index 9fb0441b98..47bb916636 100644 --- a/block-sha1/sha1.h +++ b/block-sha1/sha1.h @@ -16,7 +16,9 @@ void blk_SHA1_Init(blk_SHA_CTX *ctx); void blk_SHA1_Update(blk_SHA_CTX *ctx, const void *dataIn, size_t len); void blk_SHA1_Final(unsigned char hashout[20], blk_SHA_CTX *ctx); +#ifndef platform_SHA_CTX #define platform_SHA_CTX blk_SHA_CTX #define platform_SHA1_Init blk_SHA1_Init #define platform_SHA1_Update blk_SHA1_Update #define platform_SHA1_Final blk_SHA1_Final +#endif diff --git a/csum-file.c b/csum-file.c index bf82ad8f9f..c203ebf11b 100644 --- a/csum-file.c +++ b/csum-file.c @@ -50,7 +50,7 @@ void hashflush(struct hashfile *f) if (offset) { if (!f->skip_hash) - the_hash_algo->update_fn(&f->ctx, f->buffer, offset); + the_hash_algo->unsafe_update_fn(&f->ctx, f->buffer, offset); flush(f, f->buffer, offset); f->offset = 0; } @@ -73,7 +73,7 @@ int finalize_hashfile(struct hashfile *f, unsigned char *result, if (f->skip_hash) hashclr(f->buffer, the_repository->hash_algo); else - the_hash_algo->final_fn(f->buffer, &f->ctx); + the_hash_algo->unsafe_final_fn(f->buffer, &f->ctx); if (result) hashcpy(result, f->buffer, the_repository->hash_algo); @@ -128,7 +128,7 @@ void hashwrite(struct hashfile *f, const void *buf, unsigned int count) * f->offset is necessarily zero. */ if (!f->skip_hash) - the_hash_algo->update_fn(&f->ctx, buf, nr); + the_hash_algo->unsafe_update_fn(&f->ctx, buf, nr); flush(f, buf, nr); } else { /* @@ -174,7 +174,7 @@ static struct hashfile *hashfd_internal(int fd, const char *name, f->name = name; f->do_crc = 0; f->skip_hash = 0; - the_hash_algo->init_fn(&f->ctx); + the_hash_algo->unsafe_init_fn(&f->ctx); f->buffer_len = buffer_len; f->buffer = xmalloc(buffer_len); @@ -208,7 +208,7 @@ void hashfile_checkpoint(struct hashfile *f, struct hashfile_checkpoint *checkpo { hashflush(f); checkpoint->offset = f->total; - the_hash_algo->clone_fn(&checkpoint->ctx, &f->ctx); + the_hash_algo->unsafe_clone_fn(&checkpoint->ctx, &f->ctx); } int hashfile_truncate(struct hashfile *f, struct hashfile_checkpoint *checkpoint) @@ -219,7 +219,7 @@ int hashfile_truncate(struct hashfile *f, struct hashfile_checkpoint *checkpoint lseek(f->fd, offset, SEEK_SET) != offset) return -1; f->total = offset; - the_hash_algo->clone_fn(&f->ctx, &checkpoint->ctx); + the_hash_algo->unsafe_clone_fn(&f->ctx, &checkpoint->ctx); f->offset = 0; /* hashflush() was called in checkpoint */ return 0; } @@ -245,9 +245,9 @@ int hashfile_checksum_valid(const unsigned char *data, size_t total_len) if (total_len < the_hash_algo->rawsz) return 0; /* say "too short"? */ - the_hash_algo->init_fn(&ctx); - the_hash_algo->update_fn(&ctx, data, data_len); - the_hash_algo->final_fn(got, &ctx); + the_hash_algo->unsafe_init_fn(&ctx); + the_hash_algo->unsafe_update_fn(&ctx, data, data_len); + the_hash_algo->unsafe_final_fn(got, &ctx); return hasheq(got, data + data_len, the_repository->hash_algo); } diff --git a/hash.h b/hash.h index 72ffbc862e..f97f858307 100644 --- a/hash.h +++ b/hash.h @@ -15,6 +15,36 @@ #include "block-sha1/sha1.h" #endif +#if defined(SHA1_APPLE_UNSAFE) +# include +# define platform_SHA_CTX_unsafe CC_SHA1_CTX +# define platform_SHA1_Init_unsafe CC_SHA1_Init +# define platform_SHA1_Update_unsafe CC_SHA1_Update +# define platform_SHA1_Final_unsafe CC_SHA1_Final +#elif defined(SHA1_OPENSSL_UNSAFE) +# include +# if defined(OPENSSL_API_LEVEL) && OPENSSL_API_LEVEL >= 3 +# define SHA1_NEEDS_CLONE_HELPER_UNSAFE +# include "sha1/openssl.h" +# define platform_SHA_CTX_unsafe openssl_SHA1_CTX +# define platform_SHA1_Init_unsafe openssl_SHA1_Init +# define platform_SHA1_Clone_unsafe openssl_SHA1_Clone +# define platform_SHA1_Update_unsafe openssl_SHA1_Update +# define platform_SHA1_Final_unsafe openssl_SHA1_Final +# else +# define platform_SHA_CTX_unsafe SHA_CTX +# define platform_SHA1_Init_unsafe SHA1_Init +# define platform_SHA1_Update_unsafe SHA1_Update +# define platform_SHA1_Final_unsafe SHA1_Final +# endif +#elif defined(SHA1_BLK_UNSAFE) +# include "block-sha1/sha1.h" +# define platform_SHA_CTX_unsafe blk_SHA_CTX +# define platform_SHA1_Init_unsafe blk_SHA1_Init +# define platform_SHA1_Update_unsafe blk_SHA1_Update +# define platform_SHA1_Final_unsafe blk_SHA1_Final +#endif + #if defined(SHA256_NETTLE) #include "sha256/nettle.h" #elif defined(SHA256_GCRYPT) @@ -44,14 +74,32 @@ #define platform_SHA1_Final SHA1_Final #endif +#ifndef platform_SHA_CTX_unsafe +# define platform_SHA_CTX_unsafe platform_SHA_CTX +# define platform_SHA1_Init_unsafe platform_SHA1_Init +# define platform_SHA1_Update_unsafe platform_SHA1_Update +# define platform_SHA1_Final_unsafe platform_SHA1_Final +# ifdef platform_SHA1_Clone +# define platform_SHA1_Clone_unsafe platform_SHA1_Clone +# endif +#endif + #define git_SHA_CTX platform_SHA_CTX #define git_SHA1_Init platform_SHA1_Init #define git_SHA1_Update platform_SHA1_Update #define git_SHA1_Final platform_SHA1_Final +#define git_SHA_CTX_unsafe platform_SHA_CTX_unsafe +#define git_SHA1_Init_unsafe platform_SHA1_Init_unsafe +#define git_SHA1_Update_unsafe platform_SHA1_Update_unsafe +#define git_SHA1_Final_unsafe platform_SHA1_Final_unsafe + #ifdef platform_SHA1_Clone #define git_SHA1_Clone platform_SHA1_Clone #endif +#ifdef platform_SHA1_Clone_unsafe +# define git_SHA1_Clone_unsafe platform_SHA1_Clone_unsafe +#endif #ifndef platform_SHA256_CTX #define platform_SHA256_CTX SHA256_CTX @@ -81,6 +129,13 @@ static inline void git_SHA1_Clone(git_SHA_CTX *dst, const git_SHA_CTX *src) memcpy(dst, src, sizeof(*dst)); } #endif +#ifndef SHA1_NEEDS_CLONE_HELPER_UNSAFE +static inline void git_SHA1_Clone_unsafe(git_SHA_CTX_unsafe *dst, + const git_SHA_CTX_unsafe *src) +{ + memcpy(dst, src, sizeof(*dst)); +} +#endif #ifndef SHA256_NEEDS_CLONE_HELPER static inline void git_SHA256_Clone(git_SHA256_CTX *dst, const git_SHA256_CTX *src) @@ -178,6 +233,8 @@ enum get_oid_result { /* A suitably aligned type for stack allocations of hash contexts. */ union git_hash_ctx { git_SHA_CTX sha1; + git_SHA_CTX_unsafe sha1_unsafe; + git_SHA256_CTX sha256; }; typedef union git_hash_ctx git_hash_ctx; @@ -222,6 +279,21 @@ struct git_hash_algo { /* The hash finalization function for object IDs. */ git_hash_final_oid_fn final_oid_fn; + /* The non-cryptographic hash initialization function. */ + git_hash_init_fn unsafe_init_fn; + + /* The non-cryptographic hash context cloning function. */ + git_hash_clone_fn unsafe_clone_fn; + + /* The non-cryptographic hash update function. */ + git_hash_update_fn unsafe_update_fn; + + /* The non-cryptographic hash finalization function. */ + git_hash_final_fn unsafe_final_fn; + + /* The non-cryptographic hash finalization function. */ + git_hash_final_oid_fn unsafe_final_oid_fn; + /* The OID of the empty tree. */ const struct object_id *empty_tree; diff --git a/object-file.c b/object-file.c index 7ac9533ab1..b1a3463852 100644 --- a/object-file.c +++ b/object-file.c @@ -115,6 +115,33 @@ static void git_hash_sha1_final_oid(struct object_id *oid, git_hash_ctx *ctx) oid->algo = GIT_HASH_SHA1; } +static void git_hash_sha1_init_unsafe(git_hash_ctx *ctx) +{ + git_SHA1_Init_unsafe(&ctx->sha1_unsafe); +} + +static void git_hash_sha1_clone_unsafe(git_hash_ctx *dst, const git_hash_ctx *src) +{ + git_SHA1_Clone_unsafe(&dst->sha1_unsafe, &src->sha1_unsafe); +} + +static void git_hash_sha1_update_unsafe(git_hash_ctx *ctx, const void *data, + size_t len) +{ + git_SHA1_Update_unsafe(&ctx->sha1_unsafe, data, len); +} + +static void git_hash_sha1_final_unsafe(unsigned char *hash, git_hash_ctx *ctx) +{ + git_SHA1_Final_unsafe(hash, &ctx->sha1_unsafe); +} + +static void git_hash_sha1_final_oid_unsafe(struct object_id *oid, git_hash_ctx *ctx) +{ + git_SHA1_Final_unsafe(oid->hash, &ctx->sha1_unsafe); + memset(oid->hash + GIT_SHA1_RAWSZ, 0, GIT_MAX_RAWSZ - GIT_SHA1_RAWSZ); + oid->algo = GIT_HASH_SHA1; +} static void git_hash_sha256_init(git_hash_ctx *ctx) { @@ -189,6 +216,11 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = { .update_fn = git_hash_unknown_update, .final_fn = git_hash_unknown_final, .final_oid_fn = git_hash_unknown_final_oid, + .unsafe_init_fn = git_hash_unknown_init, + .unsafe_clone_fn = git_hash_unknown_clone, + .unsafe_update_fn = git_hash_unknown_update, + .unsafe_final_fn = git_hash_unknown_final, + .unsafe_final_oid_fn = git_hash_unknown_final_oid, .empty_tree = NULL, .empty_blob = NULL, .null_oid = NULL, @@ -204,6 +236,11 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = { .update_fn = git_hash_sha1_update, .final_fn = git_hash_sha1_final, .final_oid_fn = git_hash_sha1_final_oid, + .unsafe_init_fn = git_hash_sha1_init_unsafe, + .unsafe_clone_fn = git_hash_sha1_clone_unsafe, + .unsafe_update_fn = git_hash_sha1_update_unsafe, + .unsafe_final_fn = git_hash_sha1_final_unsafe, + .unsafe_final_oid_fn = git_hash_sha1_final_oid_unsafe, .empty_tree = &empty_tree_oid, .empty_blob = &empty_blob_oid, .null_oid = &null_oid_sha1, @@ -219,6 +256,11 @@ const struct git_hash_algo hash_algos[GIT_HASH_NALGOS] = { .update_fn = git_hash_sha256_update, .final_fn = git_hash_sha256_final, .final_oid_fn = git_hash_sha256_final_oid, + .unsafe_init_fn = git_hash_sha256_init, + .unsafe_clone_fn = git_hash_sha256_clone, + .unsafe_update_fn = git_hash_sha256_update, + .unsafe_final_fn = git_hash_sha256_final, + .unsafe_final_oid_fn = git_hash_sha256_final_oid, .empty_tree = &empty_tree_oid_sha256, .empty_blob = &empty_blob_oid_sha256, .null_oid = &null_oid_sha256, @@ -1932,17 +1974,77 @@ static void write_object_file_prepare_literally(const struct git_hash_algo *algo hash_object_body(algo, &c, buf, len, oid, hdr, hdrlen); } +static int check_collision(const char *filename_a, const char *filename_b) +{ + char buf_a[4096], buf_b[4096]; + int fd_a = -1, fd_b = -1; + int ret = 0; + + fd_a = open(filename_a, O_RDONLY); + if (fd_a < 0) { + ret = error_errno(_("unable to open %s"), filename_a); + goto out; + } + + fd_b = open(filename_b, O_RDONLY); + if (fd_b < 0) { + ret = error_errno(_("unable to open %s"), filename_b); + goto out; + } + + while (1) { + ssize_t sz_a, sz_b; + + sz_a = read_in_full(fd_a, buf_a, sizeof(buf_a)); + if (sz_a < 0) { + ret = error_errno(_("unable to read %s"), filename_a); + goto out; + } + + sz_b = read_in_full(fd_b, buf_b, sizeof(buf_b)); + if (sz_b < 0) { + ret = error_errno(_("unable to read %s"), filename_b); + goto out; + } + + if (sz_a != sz_b || memcmp(buf_a, buf_b, sz_a)) { + ret = error(_("files '%s' and '%s' differ in contents"), + filename_a, filename_b); + goto out; + } + + if (sz_a < sizeof(buf_a)) + break; + } + +out: + if (fd_a > -1) + close(fd_a); + if (fd_b > -1) + close(fd_b); + return ret; +} + /* * Move the just written object into its final resting place. */ int finalize_object_file(const char *tmpfile, const char *filename) { + return finalize_object_file_flags(tmpfile, filename, 0); +} + +int finalize_object_file_flags(const char *tmpfile, const char *filename, + enum finalize_object_file_flags flags) +{ + struct stat st; int ret = 0; if (object_creation_mode == OBJECT_CREATION_USES_RENAMES) goto try_rename; else if (link(tmpfile, filename)) ret = errno; + else + unlink_or_warn(tmpfile); /* * Coda hack - coda doesn't like cross-directory links, @@ -1957,16 +2059,24 @@ int finalize_object_file(const char *tmpfile, const char *filename) */ if (ret && ret != EEXIST) { try_rename: - if (!rename(tmpfile, filename)) + if (!stat(filename, &st)) + ret = EEXIST; + else if (!rename(tmpfile, filename)) goto out; - ret = errno; + else + ret = errno; } - unlink_or_warn(tmpfile); if (ret) { if (ret != EEXIST) { + int saved_errno = errno; + unlink_or_warn(tmpfile); + errno = saved_errno; return error_errno(_("unable to write file %s"), filename); } - /* FIXME!!! Collision check here ? */ + if (!(flags & FOF_SKIP_COLLISION_CHECK) && + check_collision(tmpfile, filename)) + return -1; + unlink_or_warn(tmpfile); } out: @@ -2219,7 +2329,8 @@ static int write_loose_object(const struct object_id *oid, char *hdr, warning_errno(_("failed utime() on %s"), tmp_file.buf); } - return finalize_object_file(tmp_file.buf, filename.buf); + return finalize_object_file_flags(tmp_file.buf, filename.buf, + FOF_SKIP_COLLISION_CHECK); } static int freshen_loose_object(const struct object_id *oid) @@ -2341,7 +2452,8 @@ int stream_loose_object(struct input_stream *in_stream, size_t len, strbuf_release(&dir); } - err = finalize_object_file(tmp_file.buf, filename.buf); + err = finalize_object_file_flags(tmp_file.buf, filename.buf, + FOF_SKIP_COLLISION_CHECK); if (!err && compat) err = repo_add_loose_object_map(the_repository, oid, &compat_oid); cleanup: diff --git a/object-file.h b/object-file.h index d6414610f8..81b30d269c 100644 --- a/object-file.h +++ b/object-file.h @@ -117,7 +117,13 @@ int check_object_signature(struct repository *r, const struct object_id *oid, */ int stream_object_signature(struct repository *r, const struct object_id *oid); +enum finalize_object_file_flags { + FOF_SKIP_COLLISION_CHECK = 1, +}; + int finalize_object_file(const char *tmpfile, const char *filename); +int finalize_object_file_flags(const char *tmpfile, const char *filename, + enum finalize_object_file_flags flags); /* Helper to check and "touch" a file */ int check_and_freshen_file(const char *fn, int freshen); diff --git a/pack-write.c b/pack-write.c index 27965672f1..f415604c15 100644 --- a/pack-write.c +++ b/pack-write.c @@ -8,6 +8,7 @@ #include "csum-file.h" #include "remote.h" #include "chunk-format.h" +#include "object-file.h" #include "pack-mtimes.h" #include "pack-objects.h" #include "pack-revindex.h" @@ -528,9 +529,9 @@ static void rename_tmp_packfile(struct strbuf *name_prefix, const char *source, size_t name_prefix_len = name_prefix->len; strbuf_addstr(name_prefix, ext); - if (rename(source, name_prefix->buf)) - die_errno("unable to rename temporary file to '%s'", - name_prefix->buf); + if (finalize_object_file(source, name_prefix->buf)) + die("unable to rename temporary file to '%s'", + name_prefix->buf); strbuf_setlen(name_prefix, name_prefix_len); } diff --git a/sha1/openssl.h b/sha1/openssl.h index 006c1f4ba5..1038af47da 100644 --- a/sha1/openssl.h +++ b/sha1/openssl.h @@ -40,10 +40,12 @@ static inline void openssl_SHA1_Clone(struct openssl_SHA1_CTX *dst, EVP_MD_CTX_copy_ex(dst->ectx, src->ectx); } +#ifndef platform_SHA_CTX #define platform_SHA_CTX openssl_SHA1_CTX #define platform_SHA1_Init openssl_SHA1_Init #define platform_SHA1_Clone openssl_SHA1_Clone #define platform_SHA1_Update openssl_SHA1_Update #define platform_SHA1_Final openssl_SHA1_Final +#endif #endif /* SHA1_OPENSSL_H */ diff --git a/sha1dc_git.h b/sha1dc_git.h index 60e3ce8439..f6f880cabe 100644 --- a/sha1dc_git.h +++ b/sha1dc_git.h @@ -18,7 +18,10 @@ void git_SHA1DCFinal(unsigned char [20], SHA1_CTX *); void git_SHA1DCUpdate(SHA1_CTX *ctx, const void *data, unsigned long len); #define platform_SHA_IS_SHA1DC /* used by "test-tool sha1-is-sha1dc" */ + +#ifndef platform_SHA_CTX #define platform_SHA_CTX SHA1_CTX #define platform_SHA1_Init git_SHA1DCInit #define platform_SHA1_Update git_SHA1DCUpdate #define platform_SHA1_Final git_SHA1DCFinal +#endif diff --git a/t/t5303-pack-corruption-resilience.sh b/t/t5303-pack-corruption-resilience.sh index 61469ef4a6..e6a43ec9ae 100755 --- a/t/t5303-pack-corruption-resilience.sh +++ b/t/t5303-pack-corruption-resilience.sh @@ -44,9 +44,14 @@ create_new_pack() { } do_repack() { + for f in $pack.* + do + mv $f "$(echo $f | sed -e 's/pack-/pack-corrupt-/')" || return 1 + done && pack=$(printf "$blob_1\n$blob_2\n$blob_3\n" | git pack-objects $@ .git/objects/pack/pack) && - pack=".git/objects/pack/pack-${pack}" + pack=".git/objects/pack/pack-${pack}" && + rm -f .git/objects/pack/pack-corrupt-* } do_corrupt_object() { diff --git a/tmp-objdir.c b/tmp-objdir.c index c2fb9f9193..9da0071cba 100644 --- a/tmp-objdir.c +++ b/tmp-objdir.c @@ -206,9 +206,11 @@ static int read_dir_paths(struct string_list *out, const char *path) return 0; } -static int migrate_paths(struct strbuf *src, struct strbuf *dst); +static int migrate_paths(struct strbuf *src, struct strbuf *dst, + enum finalize_object_file_flags flags); -static int migrate_one(struct strbuf *src, struct strbuf *dst) +static int migrate_one(struct strbuf *src, struct strbuf *dst, + enum finalize_object_file_flags flags) { struct stat st; @@ -220,12 +222,18 @@ static int migrate_one(struct strbuf *src, struct strbuf *dst) return -1; } else if (errno != EEXIST) return -1; - return migrate_paths(src, dst); + return migrate_paths(src, dst, flags); } - return finalize_object_file(src->buf, dst->buf); + return finalize_object_file_flags(src->buf, dst->buf, flags); } -static int migrate_paths(struct strbuf *src, struct strbuf *dst) +static int is_loose_object_shard(const char *name) +{ + return strlen(name) == 2 && isxdigit(name[0]) && isxdigit(name[1]); +} + +static int migrate_paths(struct strbuf *src, struct strbuf *dst, + enum finalize_object_file_flags flags) { size_t src_len = src->len, dst_len = dst->len; struct string_list paths = STRING_LIST_INIT_DUP; @@ -239,11 +247,15 @@ static int migrate_paths(struct strbuf *src, struct strbuf *dst) for (i = 0; i < paths.nr; i++) { const char *name = paths.items[i].string; + enum finalize_object_file_flags flags_copy = flags; strbuf_addf(src, "/%s", name); strbuf_addf(dst, "/%s", name); - ret |= migrate_one(src, dst); + if (is_loose_object_shard(name)) + flags_copy |= FOF_SKIP_COLLISION_CHECK; + + ret |= migrate_one(src, dst, flags_copy); strbuf_setlen(src, src_len); strbuf_setlen(dst, dst_len); @@ -271,7 +283,7 @@ int tmp_objdir_migrate(struct tmp_objdir *t) strbuf_addbuf(&src, &t->path); strbuf_addstr(&dst, repo_get_object_directory(the_repository)); - ret = migrate_paths(&src, &dst); + ret = migrate_paths(&src, &dst, 0); strbuf_release(&src); strbuf_release(&dst);