From: Junio C Hamano Date: Wed, 23 Aug 2017 21:13:10 +0000 (-0700) Subject: Merge branch 'sb/sha1-file-cleanup' X-Git-Tag: v2.15.0-rc0~147 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/3830759c1c91726a97adb2e97e2de08aec60f25a?hp=-c Merge branch 'sb/sha1-file-cleanup' Code clean-up. * sb/sha1-file-cleanup: sha1_file: make read_info_alternates static --- 3830759c1c91726a97adb2e97e2de08aec60f25a diff --combined cache.h index f99404f89a,11a2bcd38b..ab3b52ff92 --- a/cache.h +++ b/cache.h @@@ -10,10 -10,8 +10,10 @@@ #include "trace.h" #include "string-list.h" #include "pack-revindex.h" +#include "hash.h" +#include "path.h" +#include "sha1-array.h" -#include SHA1_HEADER #ifndef platform_SHA_CTX /* * platform's underlying implementation of SHA-1; could be OpenSSL, @@@ -68,12 -66,8 +68,12 @@@ unsigned long git_deflate_bound(git_zst #define GIT_SHA1_RAWSZ 20 #define GIT_SHA1_HEXSZ (2 * GIT_SHA1_RAWSZ) +/* The length in byte and in hex digits of the largest possible hash value. */ +#define GIT_MAX_RAWSZ GIT_SHA1_RAWSZ +#define GIT_MAX_HEXSZ GIT_SHA1_HEXSZ + struct object_id { - unsigned char hash[GIT_SHA1_RAWSZ]; + unsigned char hash[GIT_MAX_RAWSZ]; }; #if defined(DT_UNKNOWN) && !defined(NO_D_TYPE_IN_DIRENT) @@@ -349,7 -343,6 +349,7 @@@ struct index_state extern struct index_state the_index; /* Name hashing */ +extern int test_lazy_init_name_hash(struct index_state *istate, int try_threaded); extern void add_name_hash(struct index_state *istate, struct cache_entry *ce); extern void remove_name_hash(struct index_state *istate, struct cache_entry *ce); extern void free_name_hash(struct index_state *istate); @@@ -416,7 -409,6 +416,7 @@@ static inline enum object_type object_t #define GIT_NAMESPACE_ENVIRONMENT "GIT_NAMESPACE" #define GIT_WORK_TREE_ENVIRONMENT "GIT_WORK_TREE" #define GIT_PREFIX_ENVIRONMENT "GIT_PREFIX" +#define GIT_SUPER_PREFIX_ENVIRONMENT "GIT_INTERNAL_SUPER_PREFIX" #define DEFAULT_GIT_DIR_ENVIRONMENT ".git" #define DB_ENVIRONMENT "GIT_OBJECT_DIRECTORY" #define INDEX_ENVIRONMENT "GIT_INDEX_FILE" @@@ -432,7 -424,6 +432,7 @@@ #define GITATTRIBUTES_FILE ".gitattributes" #define INFOATTRIBUTES_FILE "info/attributes" #define ATTRIBUTE_MACRO_PREFIX "[attr]" +#define GITMODULES_FILE ".gitmodules" #define GIT_NOTES_REF_ENVIRONMENT "GIT_NOTES_REF" #define GIT_NOTES_DEFAULT_REF "refs/notes/commits" #define GIT_NOTES_DISPLAY_REF_ENVIRONMENT "GIT_NOTES_DISPLAY_REF" @@@ -442,7 -433,6 +442,7 @@@ #define GIT_GLOB_PATHSPECS_ENVIRONMENT "GIT_GLOB_PATHSPECS" #define GIT_NOGLOB_PATHSPECS_ENVIRONMENT "GIT_NOGLOB_PATHSPECS" #define GIT_ICASE_PATHSPECS_ENVIRONMENT "GIT_ICASE_PATHSPECS" +#define GIT_QUARANTINE_ENVIRONMENT "GIT_QUARANTINE_PATH" /* * This environment variable is expected to contain a boolean indicating @@@ -464,8 -454,6 +464,8 @@@ */ extern const char * const local_repo_env[]; +extern void setup_git_env(void); + /* * Returns true iff we have a configured git repository (either via * setup_git_directory, or in the environment via $GIT_DIR). @@@ -487,7 -475,6 +487,7 @@@ extern int get_common_dir_noenv(struct extern int get_common_dir(struct strbuf *sb, const char *gitdir); extern const char *get_git_namespace(void); extern const char *strip_namespace(const char *namespaced_ref); +extern const char *get_super_prefix(void); extern const char *get_git_work_tree(void); /* @@@ -517,44 -504,20 +517,44 @@@ extern int is_nonbare_repository_dir(st #define READ_GITFILE_ERR_NO_PATH 6 #define READ_GITFILE_ERR_NOT_A_REPO 7 #define READ_GITFILE_ERR_TOO_LARGE 8 +extern void read_gitfile_error_die(int error_code, const char *path, const char *dir); extern const char *read_gitfile_gently(const char *path, int *return_error_code); #define read_gitfile(path) read_gitfile_gently((path), NULL) -extern const char *resolve_gitdir(const char *suspect); +extern const char *resolve_gitdir_gently(const char *suspect, int *return_error_code); +#define resolve_gitdir(path) resolve_gitdir_gently((path), NULL) + extern void set_git_work_tree(const char *tree); #define ALTERNATE_DB_ENVIRONMENT "GIT_ALTERNATE_OBJECT_DIRECTORIES" -extern const char **get_pathspec(const char *prefix, const char **pathspec); extern void setup_work_tree(void); +/* + * Find the commondir and gitdir of the repository that contains the current + * working directory, without changing the working directory or other global + * state. The result is appended to commondir and gitdir. If the discovered + * gitdir does not correspond to a worktree, then 'commondir' and 'gitdir' will + * both have the same result appended to the buffer. The return value is + * either 0 upon success and non-zero if no repository was found. + */ +extern int discover_git_directory(struct strbuf *commondir, + struct strbuf *gitdir); extern const char *setup_git_directory_gently(int *); extern const char *setup_git_directory(void); extern char *prefix_path(const char *prefix, int len, const char *path); extern char *prefix_path_gently(const char *prefix, int len, int *remaining, const char *path); -extern const char *prefix_filename(const char *prefix, int len, const char *path); + +/* + * Concatenate "prefix" (if len is non-zero) and "path", with no + * connecting characters (so "prefix" should end with a "/"). + * Unlike prefix_path, this should be used if the named file does + * not have to interact with index entry; i.e. name of a random file + * on the filesystem. + * + * The return value is always a newly allocated string (even if the + * prefix was empty). + */ +extern char *prefix_filename(const char *prefix, const char *path); + extern int check_filename(const char *prefix, const char *name); extern void verify_filename(const char *prefix, const char *name, @@@ -604,33 -567,12 +604,33 @@@ extern int read_index_unmerged(struct i #define CLOSE_LOCK (1 << 1) extern int write_locked_index(struct index_state *, struct lock_file *lock, unsigned flags); extern int discard_index(struct index_state *); +extern void move_index_extensions(struct index_state *dst, struct index_state *src); extern int unmerged_index(const struct index_state *); extern int verify_path(const char *path); +extern int strcmp_offset(const char *s1, const char *s2, size_t *first_change); extern int index_dir_exists(struct index_state *istate, const char *name, int namelen); extern void adjust_dirname_case(struct index_state *istate, char *name); extern struct cache_entry *index_file_exists(struct index_state *istate, const char *name, int namelen, int igncase); + +/* + * Searches for an entry defined by name and namelen in the given index. + * If the return value is positive (including 0) it is the position of an + * exact match. If the return value is negative, the negated value minus 1 + * is the position where the entry would be inserted. + * Example: The current index consists of these files and its stages: + * + * b#0, d#0, f#1, f#3 + * + * index_name_pos(&index, "a", 1) -> -1 + * index_name_pos(&index, "b", 1) -> 0 + * index_name_pos(&index, "c", 1) -> -2 + * index_name_pos(&index, "d", 1) -> 1 + * index_name_pos(&index, "e", 1) -> -3 + * index_name_pos(&index, "f", 1) -> -3 + * index_name_pos(&index, "g", 1) -> -5 + */ extern int index_name_pos(const struct index_state *, const char *name, int namelen); + #define ADD_CACHE_OK_TO_ADD 1 /* Ok to add */ #define ADD_CACHE_OK_TO_REPLACE 2 /* Ok to replace file/directory */ #define ADD_CACHE_SKIP_DFCHECK 4 /* Ok to skip DF conflict checks */ @@@ -639,10 -581,7 +639,10 @@@ #define ADD_CACHE_KEEP_CACHE_TREE 32 /* Do not invalidate cache-tree */ extern int add_index_entry(struct index_state *, struct cache_entry *ce, int option); extern void rename_index_entry_at(struct index_state *, int pos, const char *new_name); + +/* Remove entry, return true if there are more entries to go. */ extern int remove_index_entry_at(struct index_state *, int pos); + extern void remove_marked_cache_entries(struct index_state *istate); extern int remove_file_from_index(struct index_state *, const char *path); #define ADD_CACHE_VERBOSE 1 @@@ -650,24 -589,14 +650,24 @@@ #define ADD_CACHE_IGNORE_ERRORS 4 #define ADD_CACHE_IGNORE_REMOVAL 8 #define ADD_CACHE_INTENT 16 +/* + * These two are used to add the contents of the file at path + * to the index, marking the working tree up-to-date by storing + * the cached stat info in the resulting cache entry. A caller + * that has already run lstat(2) on the path can call + * add_to_index(), and all others can call add_file_to_index(); + * the latter will do necessary lstat(2) internally before + * calling the former. + */ extern int add_to_index(struct index_state *, const char *path, struct stat *, int flags); extern int add_file_to_index(struct index_state *, const char *path, int flags); + extern struct cache_entry *make_cache_entry(unsigned int mode, const unsigned char *sha1, const char *path, int stage, unsigned int refresh_options); extern int chmod_index_entry(struct index_state *, struct cache_entry *ce, char flip); extern int ce_same_name(const struct cache_entry *a, const struct cache_entry *b); extern void set_object_name_for_intent_to_add_entry(struct cache_entry *ce); extern int index_name_is_other(const struct index_state *, const char *, int); -extern void *read_blob_data_from_index(struct index_state *, const char *, unsigned long *); +extern void *read_blob_data_from_index(const struct index_state *, const char *, unsigned long *); /* do stat comparison even if CE_VALID is true */ #define CE_MATCH_IGNORE_VALID 01 @@@ -719,8 -648,6 +719,8 @@@ extern void update_index_if_able(struc extern int hold_locked_index(struct lock_file *, int); extern void set_alternate_index_output(const char *); +extern int verify_index_checksum; + /* Environment bits from configuration mechanism */ extern int trust_executable_bit; extern int trust_ctime; @@@ -731,6 -658,7 +731,6 @@@ extern int minimum_abbrev, default_abbr extern int ignore_case; extern int assume_unchanged; extern int prefer_symlink_refs; -extern int log_all_ref_updates; extern int warn_ambiguous_refs; extern int warn_on_object_refname_ambiguity; extern const char *apply_default_whitespace; @@@ -739,7 -667,7 +739,7 @@@ extern const char *git_attributes_file extern const char *git_hooks_path; extern int zlib_compression_level; extern int core_compression_level; -extern int core_compression_seen; +extern int pack_compression_level; extern size_t packed_git_window_size; extern size_t packed_git_limit; extern size_t delta_base_cache_limit; @@@ -773,6 -701,7 +773,6 @@@ extern int core_apply_sparse_checkout extern int precomposed_unicode; extern int protect_hfs; extern int protect_ntfs; -extern int git_db_env, git_index_env, git_graft_env, git_common_dir_env; /* * Include broken refs in all ref iterations, which will @@@ -797,14 -726,6 +797,14 @@@ enum hide_dotfiles_type }; extern enum hide_dotfiles_type hide_dotfiles; +enum log_refs_config { + LOG_REFS_UNSET = -1, + LOG_REFS_NONE = 0, + LOG_REFS_NORMAL, + LOG_REFS_ALWAYS +}; +extern enum log_refs_config log_all_ref_updates; + enum branch_track { BRANCH_TRACK_UNSPECIFIED = -1, BRANCH_TRACK_NEVER = 0, @@@ -894,6 -815,64 +894,6 @@@ extern void check_repository_format(voi #define DATA_CHANGED 0x0020 #define TYPE_CHANGED 0x0040 -/* - * Return a statically allocated filename, either generically (mkpath), in - * the repository directory (git_path), or in a submodule's repository - * directory (git_path_submodule). In all cases, note that the result - * may be overwritten by another call to _any_ of the functions. Consider - * using the safer "dup" or "strbuf" formats below (in some cases, the - * unsafe versions have already been removed). - */ -extern const char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2))); -extern const char *git_path(const char *fmt, ...) __attribute__((format (printf, 1, 2))); -extern const char *git_common_path(const char *fmt, ...) __attribute__((format (printf, 1, 2))); - -extern char *mksnpath(char *buf, size_t n, const char *fmt, ...) - __attribute__((format (printf, 3, 4))); -extern void strbuf_git_path(struct strbuf *sb, const char *fmt, ...) - __attribute__((format (printf, 2, 3))); -extern void strbuf_git_common_path(struct strbuf *sb, const char *fmt, ...) - __attribute__((format (printf, 2, 3))); -extern char *git_path_buf(struct strbuf *buf, const char *fmt, ...) - __attribute__((format (printf, 2, 3))); -extern int strbuf_git_path_submodule(struct strbuf *sb, const char *path, - const char *fmt, ...) - __attribute__((format (printf, 3, 4))); -extern char *git_pathdup(const char *fmt, ...) - __attribute__((format (printf, 1, 2))); -extern char *mkpathdup(const char *fmt, ...) - __attribute__((format (printf, 1, 2))); -extern char *git_pathdup_submodule(const char *path, const char *fmt, ...) - __attribute__((format (printf, 2, 3))); - -extern void report_linked_checkout_garbage(void); - -/* - * You can define a static memoized git path like: - * - * static GIT_PATH_FUNC(git_path_foo, "FOO"); - * - * or use one of the global ones below. - */ -#define GIT_PATH_FUNC(func, filename) \ - const char *func(void) \ - { \ - static char *ret; \ - if (!ret) \ - ret = git_pathdup(filename); \ - return ret; \ - } - -const char *git_path_cherry_pick_head(void); -const char *git_path_revert_head(void); -const char *git_path_squash_msg(void); -const char *git_path_merge_msg(void); -const char *git_path_merge_rr(void); -const char *git_path_merge_mode(void); -const char *git_path_merge_head(void); -const char *git_path_fetch_head(void); -const char *git_path_shallow(void); - /* * Return the name of the file in the local object database that would * be used to store a loose object with the specified sha1. The @@@ -921,8 -900,8 +921,8 @@@ extern char *sha1_pack_index_name(cons * The result will be at least `len` characters long, and will be NUL * terminated. * - * The non-`_r` version returns a static buffer which will be overwritten by - * subsequent calls. + * The non-`_r` version returns a static buffer which remains valid until 4 + * more calls to find_unique_abbrev are made. * * The `_r` variant writes to a buffer supplied by the caller, which must be at * least `GIT_SHA1_HEXSZ + 1` bytes. The return value is the number of bytes @@@ -934,12 -913,19 +934,12 @@@ extern const char *find_unique_abbrev(const unsigned char *sha1, int len); extern int find_unique_abbrev_r(char *hex, const unsigned char *sha1, int len); -extern const unsigned char null_sha1[GIT_SHA1_RAWSZ]; +extern const unsigned char null_sha1[GIT_MAX_RAWSZ]; extern const struct object_id null_oid; static inline int hashcmp(const unsigned char *sha1, const unsigned char *sha2) { - int i; - - for (i = 0; i < GIT_SHA1_RAWSZ; i++, sha1++, sha2++) { - if (*sha1 != *sha2) - return *sha1 - *sha2; - } - - return 0; + return memcmp(sha1, sha2, GIT_SHA1_RAWSZ); } static inline int oidcmp(const struct object_id *oid1, const struct object_id *oid2) @@@ -967,13 -953,6 +967,13 @@@ static inline void oidcpy(struct object hashcpy(dst->hash, src->hash); } +static inline struct object_id *oiddup(const struct object_id *src) +{ + struct object_id *dst = xmalloc(sizeof(struct object_id)); + oidcpy(dst, src); + return dst; +} + static inline void hashclr(unsigned char *hash) { memset(hash, 0, GIT_SHA1_RAWSZ); @@@ -1022,6 -1001,9 +1022,6 @@@ static inline int is_empty_tree_oid(con return !hashcmp(oid->hash, EMPTY_TREE_SHA1_BIN); } - -int git_mkstemp(char *path, size_t n, const char *template); - /* set default permissions by passing mode arguments to open(2) */ int git_mkstemps_mode(char *pattern, int suffix_len, int mode); int git_mkstemp_mode(char *pattern, int mode); @@@ -1046,9 -1028,8 +1046,9 @@@ int adjust_shared_perm(const char *path /* * Create the directory containing the named path, using care to be - * somewhat safe against races. Return one of the scld_error values - * to indicate success/failure. + * somewhat safe against races. Return one of the scld_error values to + * indicate success/failure. On error, set errno to describe the + * problem. * * SCLD_VANISHED indicates that one of the ancestor directories of the * path existed at one point during the function call and then @@@ -1072,64 -1053,17 +1072,64 @@@ enum scld_error enum scld_error safe_create_leading_directories(char *path); enum scld_error safe_create_leading_directories_const(const char *path); +/* + * Callback function for raceproof_create_file(). This function is + * expected to do something that makes dirname(path) permanent despite + * the fact that other processes might be cleaning up empty + * directories at the same time. Usually it will create a file named + * path, but alternatively it could create another file in that + * directory, or even chdir() into that directory. The function should + * return 0 if the action was completed successfully. On error, it + * should return a nonzero result and set errno. + * raceproof_create_file() treats two errno values specially: + * + * - ENOENT -- dirname(path) does not exist. In this case, + * raceproof_create_file() tries creating dirname(path) + * (and any parent directories, if necessary) and calls + * the function again. + * + * - EISDIR -- the file already exists and is a directory. In this + * case, raceproof_create_file() removes the directory if + * it is empty (and recursively any empty directories that + * it contains) and calls the function again. + * + * Any other errno causes raceproof_create_file() to fail with the + * callback's return value and errno. + * + * Obviously, this function should be OK with being called again if it + * fails with ENOENT or EISDIR. In other scenarios it will not be + * called again. + */ +typedef int create_file_fn(const char *path, void *cb); + +/* + * Create a file in dirname(path) by calling fn, creating leading + * directories if necessary. Retry a few times in case we are racing + * with another process that is trying to clean up the directory that + * contains path. See the documentation for create_file_fn for more + * details. + * + * Return the value and set the errno that resulted from the most + * recent call of fn. fn is always called at least once, and will be + * called more than once if it returns ENOENT or EISDIR. + */ +int raceproof_create_file(const char *path, create_file_fn fn, void *cb); + int mkdir_in_gitdir(const char *path); -extern char *expand_user_path(const char *path); +extern char *expand_user_path(const char *path, int real_home); const char *enter_repo(const char *path, int strict); static inline int is_absolute_path(const char *path) { return is_dir_sep(path[0]) || has_dos_drive_prefix(path); } int is_directory(const char *); +char *strbuf_realpath(struct strbuf *resolved, const char *path, + int die_on_error); const char *real_path(const char *path); const char *real_path_if_valid(const char *path); +char *real_pathdup(const char *path, int die_on_error); const char *absolute_path(const char *path); +char *absolute_pathdup(const char *path); const char *remove_leading_path(const char *in, const char *prefix); const char *relative_path(const char *in, const char *prefix, struct strbuf *sb); int normalize_path_copy_len(char *dst, const char *src, int *prefix_len); @@@ -1139,14 -1073,6 +1139,14 @@@ char *strip_path_suffix(const char *pat int daemon_avoid_alias(const char *path); extern int is_ntfs_dotgit(const char *name); +/* + * Returns true iff "str" could be confused as a command-line option when + * passed to a sub-program like "ssh". Note that this has nothing to do with + * shell-quoting, which should be handled separately; we're assuming here that + * the string makes it verbatim to the sub-program. + */ +int looks_like_command_line_option(const char *str); + /** * Return a newly allocated string with the evaluation of * "$XDG_CONFIG_HOME/git/$filename" if $XDG_CONFIG_HOME is non-empty, otherwise @@@ -1154,19 -1080,13 +1154,19 @@@ */ extern char *xdg_config_home(const char *filename); -/* object replacement */ -#define LOOKUP_REPLACE_OBJECT 1 -#define LOOKUP_UNKNOWN_OBJECT 2 -extern void *read_sha1_file_extended(const unsigned char *sha1, enum object_type *type, unsigned long *size, unsigned flag); +/** + * Return a newly allocated string with the evaluation of + * "$XDG_CACHE_HOME/git/$filename" if $XDG_CACHE_HOME is non-empty, otherwise + * "$HOME/.cache/git/$filename". Return NULL upon error. + */ +extern char *xdg_cache_home(const char *filename); + +extern void *read_sha1_file_extended(const unsigned char *sha1, + enum object_type *type, + unsigned long *size, int lookup_replace); static inline void *read_sha1_file(const unsigned char *sha1, enum object_type *type, unsigned long *size) { - return read_sha1_file_extended(sha1, type, size, LOOKUP_REPLACE_OBJECT); + return read_sha1_file_extended(sha1, type, size, 1); } /* @@@ -1188,6 -1108,13 +1188,6 @@@ static inline const unsigned char *look return do_lookup_replace_object(sha1); } -static inline const unsigned char *lookup_replace_object_extended(const unsigned char *sha1, unsigned flag) -{ - if (!(flag & LOOKUP_REPLACE_OBJECT)) - return sha1; - return lookup_replace_object(sha1); -} - /* Read and unpack a sha1 file into memory, write memory to a sha1 file */ extern int sha1_object_info(const unsigned char *, unsigned long *); extern int hash_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *sha1); @@@ -1195,8 -1122,7 +1195,8 @@@ extern int write_sha1_file(const void * extern int hash_sha1_file_literally(const void *buf, unsigned long len, const char *type, unsigned char *sha1, unsigned flags); extern int pretend_sha1_file(void *, unsigned long, enum object_type, unsigned char *); extern int force_object_loose(const unsigned char *sha1, time_t mtime); -extern int git_open_noatime(const char *name); +extern int git_open_cloexec(const char *name, int flags); +#define git_open(name) git_open_cloexec(name, O_RDONLY) extern void *map_sha1_file(const unsigned char *sha1, unsigned long *size); extern int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz); extern int parse_sha1_header(const char *hdr, unsigned long *sizep); @@@ -1211,23 -1137,15 +1211,23 @@@ extern int finalize_object_file(const c extern int has_sha1_pack(const unsigned char *sha1); /* - * Return true iff we have an object named sha1, whether local or in - * an alternate object database, and whether packed or loose. This - * function does not respect replace references. + * Open the loose object at path, check its sha1, and return the contents, + * type, and size. If the object is a blob, then "contents" may return NULL, + * to allow streaming of large blobs. * - * If the QUICK flag is set, do not re-check the pack directory - * when we cannot find the object (this means we may give a false - * negative answer if another process is simultaneously repacking). + * Returns 0 on success, negative on error (details may be written to stderr). + */ +int read_loose_object(const char *path, + const unsigned char *expected_sha1, + enum object_type *type, + unsigned long *size, + void **contents); + +/* + * Convenience for sha1_object_info_extended() with a NULL struct + * object_info. OBJECT_INFO_SKIP_CACHED is automatically set; pass + * nonzero flags to also set other flags. */ -#define HAS_SHA1_QUICK 0x1 extern int has_sha1_file_with_flags(const unsigned char *sha1, int flags); static inline int has_sha1_file(const unsigned char *sha1) { @@@ -1236,7 -1154,6 +1236,7 @@@ /* Same as the above, except for struct object_id. */ extern int has_object_file(const struct object_id *oid); +extern int has_object_file_with_flags(const struct object_id *oid, int flags); /* * Return true iff an alternate object database has a loose object @@@ -1249,9 -1166,6 +1249,9 @@@ extern int has_pack_index(const unsigne extern void assert_sha1_type(const unsigned char *sha1, enum object_type expect); +/* Helper to check and "touch" a file */ +extern int check_and_freshen_file(const char *fn, int freshen); + extern const signed char hexval_table[256]; static inline unsigned int hexval(unsigned char c) { @@@ -1272,55 -1186,40 +1272,55 @@@ static inline int hex2chr(const char *s #define MINIMUM_ABBREV minimum_abbrev #define DEFAULT_ABBREV default_abbrev +/* used when the code does not know or care what the default abbrev is */ +#define FALLBACK_DEFAULT_ABBREV 7 + struct object_context { unsigned char tree[20]; - char path[PATH_MAX]; unsigned mode; /* * symlink_path is only used by get_tree_entry_follow_symlinks, * and only for symlinks that point outside the repository. */ struct strbuf symlink_path; + /* + * If GET_OID_RECORD_PATH is set, this will record path (if any) + * found when resolving the name. The caller is responsible for + * releasing the memory. + */ + char *path; }; -#define GET_SHA1_QUIETLY 01 -#define GET_SHA1_COMMIT 02 -#define GET_SHA1_COMMITTISH 04 -#define GET_SHA1_TREE 010 -#define GET_SHA1_TREEISH 020 -#define GET_SHA1_BLOB 040 -#define GET_SHA1_FOLLOW_SYMLINKS 0100 -#define GET_SHA1_ONLY_TO_DIE 04000 - -extern int get_sha1(const char *str, unsigned char *sha1); -extern int get_sha1_commit(const char *str, unsigned char *sha1); -extern int get_sha1_committish(const char *str, unsigned char *sha1); -extern int get_sha1_tree(const char *str, unsigned char *sha1); -extern int get_sha1_treeish(const char *str, unsigned char *sha1); -extern int get_sha1_blob(const char *str, unsigned char *sha1); -extern void maybe_die_on_misspelt_object_name(const char *name, const char *prefix); -extern int get_sha1_with_context(const char *str, unsigned flags, unsigned char *sha1, struct object_context *orc); +#define GET_OID_QUIETLY 01 +#define GET_OID_COMMIT 02 +#define GET_OID_COMMITTISH 04 +#define GET_OID_TREE 010 +#define GET_OID_TREEISH 020 +#define GET_OID_BLOB 040 +#define GET_OID_FOLLOW_SYMLINKS 0100 +#define GET_OID_RECORD_PATH 0200 +#define GET_OID_ONLY_TO_DIE 04000 + +#define GET_OID_DISAMBIGUATORS \ + (GET_OID_COMMIT | GET_OID_COMMITTISH | \ + GET_OID_TREE | GET_OID_TREEISH | \ + GET_OID_BLOB) extern int get_oid(const char *str, struct object_id *oid); +extern int get_oid_commit(const char *str, struct object_id *oid); +extern int get_oid_committish(const char *str, struct object_id *oid); +extern int get_oid_tree(const char *str, struct object_id *oid); +extern int get_oid_treeish(const char *str, struct object_id *oid); +extern int get_oid_blob(const char *str, struct object_id *oid); +extern void maybe_die_on_misspelt_object_name(const char *name, const char *prefix); +extern int get_oid_with_context(const char *str, unsigned flags, struct object_id *oid, struct object_context *oc); + -typedef int each_abbrev_fn(const unsigned char *sha1, void *); +typedef int each_abbrev_fn(const struct object_id *oid, void *); extern int for_each_abbrev(const char *prefix, each_abbrev_fn, void *); +extern int set_disambiguate_hint_config(const char *var, const char *value); + /* * Try to read a SHA1 in hexadecimal format from the 40 characters * starting at hex. Write the 20-byte result to sha1 in binary form. @@@ -1347,46 -1246,7 +1347,46 @@@ extern char *oid_to_hex_r(char *out, co extern char *sha1_to_hex(const unsigned char *sha1); /* static buffer result! */ extern char *oid_to_hex(const struct object_id *oid); /* same static buffer as sha1_to_hex */ -extern int interpret_branch_name(const char *str, int len, struct strbuf *); +/* + * Parse a 40-character hexadecimal object ID starting from hex, updating the + * pointer specified by end when parsing stops. The resulting object ID is + * stored in oid. Returns 0 on success. Parsing will stop on the first NUL or + * other invalid character. end is only updated on success; otherwise, it is + * unmodified. + */ +extern int parse_oid_hex(const char *hex, struct object_id *oid, const char **end); + +/* + * This reads short-hand syntax that not only evaluates to a commit + * object name, but also can act as if the end user spelled the name + * of the branch from the command line. + * + * - "@{-N}" finds the name of the Nth previous branch we were on, and + * places the name of the branch in the given buf and returns the + * number of characters parsed if successful. + * + * - "@{upstream}" finds the name of the other ref that + * is configured to merge with (missing defaults + * to the current branch), and places the name of the branch in the + * given buf and returns the number of characters parsed if + * successful. + * + * If the input is not of the accepted format, it returns a negative + * number to signal an error. + * + * If the input was ok but there are not N branch switches in the + * reflog, it returns 0. + * + * If "allowed" is non-zero, it is a treated as a bitfield of allowable + * expansions: local branches ("refs/heads/"), remote branches + * ("refs/remotes/"), or "HEAD". If no "allowed" bits are set, any expansion is + * allowed, even ones to refs outside of those namespaces. + */ +#define INTERPRET_BRANCH_LOCAL (1<<0) +#define INTERPRET_BRANCH_REMOTE (1<<1) +#define INTERPRET_BRANCH_HEAD (1<<2) +extern int interpret_branch_name(const char *str, int len, struct strbuf *, + unsigned allowed); extern int get_oid_mb(const char *str, struct object_id *oid); extern int validate_headref(const char *ref); @@@ -1428,18 -1288,18 +1428,18 @@@ struct date_mode #define DATE_MODE(t) date_mode_from_type(DATE_##t) struct date_mode *date_mode_from_type(enum date_mode_type type); -const char *show_date(unsigned long time, int timezone, const struct date_mode *mode); -void show_date_relative(unsigned long time, int tz, const struct timeval *now, +const char *show_date(timestamp_t time, int timezone, const struct date_mode *mode); +void show_date_relative(timestamp_t time, int tz, const struct timeval *now, struct strbuf *timebuf); int parse_date(const char *date, struct strbuf *out); -int parse_date_basic(const char *date, unsigned long *timestamp, int *offset); -int parse_expiry_date(const char *date, unsigned long *timestamp); +int parse_date_basic(const char *date, timestamp_t *timestamp, int *offset); +int parse_expiry_date(const char *date, timestamp_t *timestamp); void datestamp(struct strbuf *out); #define approxidate(s) approxidate_careful((s), NULL) -unsigned long approxidate_careful(const char *, int *); -unsigned long approxidate_relative(const char *date, const struct timeval *now); +timestamp_t approxidate_careful(const char *, int *); +timestamp_t approxidate_relative(const char *date, const struct timeval *now); void parse_date_format(const char *format, struct date_mode *mode); -int date_overflows(unsigned long date); +int date_overflows(timestamp_t date); #define IDENT_STRICT 1 #define IDENT_NO_DATE 2 @@@ -1492,7 -1352,6 +1492,7 @@@ struct checkout struct index_state *istate; const char *base_dir; int base_dir_len; + struct delayed_checkout *delayed_checkout; unsigned force:1, quiet:1, not_new:1, @@@ -1502,8 -1361,6 +1502,8 @@@ #define TEMPORARY_FILENAME_LENGTH 25 extern int checkout_entry(struct cache_entry *ce, const struct checkout *state, char *topath); +extern void enable_delayed_checkout(struct checkout *state); +extern int finish_delayed_checkout(struct checkout *state); struct cache_def { struct strbuf path; @@@ -1526,35 -1383,14 +1526,34 @@@ extern void remove_scheduled_dirs(void) extern struct alternate_object_database { struct alternate_object_database *next; - char *name; - char base[FLEX_ARRAY]; /* more */ + + /* see alt_scratch_buf() */ + struct strbuf scratch; + size_t base_len; + + /* + * Used to store the results of readdir(3) calls when searching + * for unique abbreviated hashes. This cache is never + * invalidated, thus it's racy and not necessarily accurate. + * That's fine for its purpose; don't use it for tasks requiring + * greater accuracy! + */ + char loose_objects_subdir_seen[256]; + struct oid_array loose_objects_cache; + + char path[FLEX_ARRAY]; } *alt_odb_list; extern void prepare_alt_odb(void); - extern void read_info_alternates(const char * relative_base, int depth); extern char *compute_alternate_path(const char *path, struct strbuf *err); typedef int alt_odb_fn(struct alternate_object_database *, void *); extern int foreach_alt_odb(alt_odb_fn, void*); +/* + * Allocate a "struct alternate_object_database" but do _not_ actually + * add it to the list of alternates. + */ +struct alternate_object_database *alloc_alt_odb(const char *dir); + /* * Add the directory to the on-disk alternates file; the new entry will also * take effect in the current process. @@@ -1568,14 -1404,6 +1567,14 @@@ extern void add_to_alternates_file(cons */ extern void add_to_alternates_memory(const char *dir); +/* + * Returns a scratch strbuf pre-filled with the alternate object directory, + * including a trailing slash, which can be used to access paths in the + * alternate. Always use this over direct access to alt->scratch, as it + * cleans up any previous use of the scratch buffer. + */ +extern struct strbuf *alt_scratch_buf(struct alternate_object_database *alt); + struct pack_window { struct pack_window *next; unsigned char *base; @@@ -1632,41 -1460,11 +1631,41 @@@ extern void prepare_packed_git(void) extern void reprepare_packed_git(void); extern void install_packed_git(struct packed_git *pack); +/* + * Give a rough count of objects in the repository. This sacrifices accuracy + * for speed. + */ +unsigned long approximate_object_count(void); + extern struct packed_git *find_sha1_pack(const unsigned char *sha1, struct packed_git *packs); extern void pack_report(void); +/* + * Create a temporary file rooted in the object database directory, or + * die on failure. The filename is taken from "pattern", which should have the + * usual "XXXXXX" trailer, and the resulting filename is written into the + * "template" buffer. Returns the open descriptor. + */ +extern int odb_mkstemp(struct strbuf *template, const char *pattern); + +/* + * Generate the filename to be used for a pack file with checksum "sha1" and + * extension "ext". The result is written into the strbuf "buf", overwriting + * any existing contents. A pointer to buf->buf is returned as a convenience. + * + * Example: odb_pack_name(out, sha1, "idx") => ".git/objects/pack/pack-1234..idx" + */ +extern char *odb_pack_name(struct strbuf *buf, const unsigned char *sha1, const char *ext); + +/* + * Create a pack .keep file named "name" (which should generally be the output + * of odb_pack_name). Returns a file descriptor opened for writing, or -1 on + * error. + */ +extern int odb_pack_keep(const char *name); + /* * mmap the index file for the specified packfile (if it is not * already mmapped). Return 0 on success. @@@ -1703,12 -1501,6 +1702,12 @@@ extern void check_pack_index_ptr(const * error. */ extern const unsigned char *nth_packed_object_sha1(struct packed_git *, uint32_t n); +/* + * Like nth_packed_object_sha1, but write the data into the object specified by + * the the first argument. Returns the first argument on success, and NULL on + * error. + */ +extern const struct object_id *nth_packed_object_oid(struct object_id *, struct packed_git *, uint32_t n); /* * Return the offset of the nth object within the specified packfile. @@@ -1750,21 -1542,15 +1749,21 @@@ extern int unpack_object_header(struct * scratch buffer, but restored to its original contents before * the function returns. */ -typedef int each_loose_object_fn(const unsigned char *sha1, +typedef int each_loose_object_fn(const struct object_id *oid, const char *path, void *data); typedef int each_loose_cruft_fn(const char *basename, const char *path, void *data); -typedef int each_loose_subdir_fn(int nr, +typedef int each_loose_subdir_fn(unsigned int nr, const char *path, void *data); +int for_each_file_in_obj_subdir(unsigned int subdir_nr, + struct strbuf *path, + each_loose_object_fn obj_cb, + each_loose_cruft_fn cruft_cb, + each_loose_subdir_fn subdir_cb, + void *data); int for_each_loose_file_in_objdir(const char *path, each_loose_object_fn obj_cb, each_loose_cruft_fn cruft_cb, @@@ -1782,7 -1568,7 +1781,7 @@@ int for_each_loose_file_in_objdir_buf(s * LOCAL_ONLY flag is set). */ #define FOR_EACH_OBJECT_LOCAL_ONLY 0x1 -typedef int each_packed_object_fn(const unsigned char *sha1, +typedef int each_packed_object_fn(const struct object_id *oid, struct packed_git *pack, uint32_t pos, void *data); @@@ -1796,7 -1582,6 +1795,7 @@@ struct object_info off_t *disk_sizep; unsigned char *delta_base_sha1; struct strbuf *typename; + void **contentp; /* Response */ enum { @@@ -1821,30 -1606,175 +1820,30 @@@ } packed; } u; }; + +/* + * Initializer for a "struct object_info" that wants no items. You may + * also memset() the memory to all-zeroes. + */ +#define OBJECT_INFO_INIT {NULL} + +/* Invoke lookup_replace_object() on the given hash */ +#define OBJECT_INFO_LOOKUP_REPLACE 1 +/* Allow reading from a loose object file of unknown/bogus type */ +#define OBJECT_INFO_ALLOW_UNKNOWN_TYPE 2 +/* Do not check cached storage */ +#define OBJECT_INFO_SKIP_CACHED 4 +/* Do not retry packed storage after checking packed and loose storage */ +#define OBJECT_INFO_QUICK 8 extern int sha1_object_info_extended(const unsigned char *, struct object_info *, unsigned flags); +extern int packed_object_info(struct packed_git *pack, off_t offset, struct object_info *); /* Dumb servers support */ extern int update_server_info(int); -/* git_config_parse_key() returns these negated: */ -#define CONFIG_INVALID_KEY 1 -#define CONFIG_NO_SECTION_OR_NAME 2 -/* git_config_set_gently(), git_config_set_multivar_gently() return the above or these: */ -#define CONFIG_NO_LOCK -1 -#define CONFIG_INVALID_FILE 3 -#define CONFIG_NO_WRITE 4 -#define CONFIG_NOTHING_SET 5 -#define CONFIG_INVALID_PATTERN 6 -#define CONFIG_GENERIC_ERROR 7 - -#define CONFIG_REGEX_NONE ((void *)1) - -struct git_config_source { - unsigned int use_stdin:1; - const char *file; - const char *blob; -}; - -enum config_origin_type { - CONFIG_ORIGIN_BLOB, - CONFIG_ORIGIN_FILE, - CONFIG_ORIGIN_STDIN, - CONFIG_ORIGIN_SUBMODULE_BLOB, - CONFIG_ORIGIN_CMDLINE -}; - -typedef int (*config_fn_t)(const char *, const char *, void *); -extern int git_default_config(const char *, const char *, void *); -extern int git_config_from_file(config_fn_t fn, const char *, void *); -extern int git_config_from_mem(config_fn_t fn, const enum config_origin_type, - const char *name, const char *buf, size_t len, void *data); -extern void git_config_push_parameter(const char *text); -extern int git_config_from_parameters(config_fn_t fn, void *data); -extern void git_config(config_fn_t fn, void *); -extern int git_config_with_options(config_fn_t fn, void *, - struct git_config_source *config_source, - int respect_includes); -extern int git_parse_ulong(const char *, unsigned long *); -extern int git_parse_maybe_bool(const char *); -extern int git_config_int(const char *, const char *); -extern int64_t git_config_int64(const char *, const char *); -extern unsigned long git_config_ulong(const char *, const char *); -extern int git_config_bool_or_int(const char *, const char *, int *); -extern int git_config_bool(const char *, const char *); -extern int git_config_maybe_bool(const char *, const char *); -extern int git_config_string(const char **, const char *, const char *); -extern int git_config_pathname(const char **, const char *, const char *); -extern int git_config_set_in_file_gently(const char *, const char *, const char *); -extern void git_config_set_in_file(const char *, const char *, const char *); -extern int git_config_set_gently(const char *, const char *); -extern void git_config_set(const char *, const char *); -extern int git_config_parse_key(const char *, char **, int *); -extern int git_config_key_is_valid(const char *key); -extern int git_config_set_multivar_gently(const char *, const char *, const char *, int); -extern void git_config_set_multivar(const char *, const char *, const char *, int); -extern int git_config_set_multivar_in_file_gently(const char *, const char *, const char *, const char *, int); -extern void git_config_set_multivar_in_file(const char *, const char *, const char *, const char *, int); -extern int git_config_rename_section(const char *, const char *); -extern int git_config_rename_section_in_file(const char *, const char *, const char *); -extern const char *git_etc_gitconfig(void); -extern int git_env_bool(const char *, int); -extern unsigned long git_env_ulong(const char *, unsigned long); -extern int git_config_system(void); -extern int config_error_nonbool(const char *); -#if defined(__GNUC__) -#define config_error_nonbool(s) (config_error_nonbool(s), const_error()) -#endif extern const char *get_log_output_encoding(void); extern const char *get_commit_output_encoding(void); -extern int git_config_parse_parameter(const char *, config_fn_t fn, void *data); - -enum config_scope { - CONFIG_SCOPE_UNKNOWN = 0, - CONFIG_SCOPE_SYSTEM, - CONFIG_SCOPE_GLOBAL, - CONFIG_SCOPE_REPO, - CONFIG_SCOPE_CMDLINE, -}; - -extern enum config_scope current_config_scope(void); -extern const char *current_config_origin_type(void); -extern const char *current_config_name(void); - -struct config_include_data { - int depth; - config_fn_t fn; - void *data; -}; -#define CONFIG_INCLUDE_INIT { 0 } -extern int git_config_include(const char *name, const char *value, void *data); - -/* - * Match and parse a config key of the form: - * - * section.(subsection.)?key - * - * (i.e., what gets handed to a config_fn_t). The caller provides the section; - * we return -1 if it does not match, 0 otherwise. The subsection and key - * out-parameters are filled by the function (and subsection is NULL if it is - * missing). - */ -extern int parse_config_key(const char *var, - const char *section, - const char **subsection, int *subsection_len, - const char **key); - -struct config_set_element { - struct hashmap_entry ent; - char *key; - struct string_list value_list; -}; - -struct configset_list_item { - struct config_set_element *e; - int value_index; -}; - -/* - * the contents of the list are ordered according to their - * position in the config files and order of parsing the files. - * (i.e. key-value pair at the last position of .git/config will - * be at the last item of the list) - */ -struct configset_list { - struct configset_list_item *items; - unsigned int nr, alloc; -}; - -struct config_set { - struct hashmap config_hash; - int hash_initialized; - struct configset_list list; -}; - -extern void git_configset_init(struct config_set *cs); -extern int git_configset_add_file(struct config_set *cs, const char *filename); -extern int git_configset_get_value(struct config_set *cs, const char *key, const char **value); -extern const struct string_list *git_configset_get_value_multi(struct config_set *cs, const char *key); -extern void git_configset_clear(struct config_set *cs); -extern int git_configset_get_string_const(struct config_set *cs, const char *key, const char **dest); -extern int git_configset_get_string(struct config_set *cs, const char *key, char **dest); -extern int git_configset_get_int(struct config_set *cs, const char *key, int *dest); -extern int git_configset_get_ulong(struct config_set *cs, const char *key, unsigned long *dest); -extern int git_configset_get_bool(struct config_set *cs, const char *key, int *dest); -extern int git_configset_get_bool_or_int(struct config_set *cs, const char *key, int *is_bool, int *dest); -extern int git_configset_get_maybe_bool(struct config_set *cs, const char *key, int *dest); -extern int git_configset_get_pathname(struct config_set *cs, const char *key, const char **dest); - -extern int git_config_get_value(const char *key, const char **value); -extern const struct string_list *git_config_get_value_multi(const char *key); -extern void git_config_clear(void); -extern void git_config_iter(config_fn_t fn, void *data); -extern int git_config_get_string_const(const char *key, const char **dest); -extern int git_config_get_string(const char *key, char **dest); -extern int git_config_get_int(const char *key, int *dest); -extern int git_config_get_ulong(const char *key, unsigned long *dest); -extern int git_config_get_bool(const char *key, int *dest); -extern int git_config_get_bool_or_int(const char *key, int *is_bool, int *dest); -extern int git_config_get_maybe_bool(const char *key, int *dest); -extern int git_config_get_pathname(const char *key, const char **dest); -extern int git_config_get_untracked_cache(void); - /* * This is a hack for test programs like test-dump-untracked-cache to * ensure that they do not modify the untracked cache when reading it. @@@ -1852,6 -1782,16 +1851,6 @@@ */ extern int ignore_untracked_cache_config; -struct key_value_info { - const char *filename; - int linenr; - enum config_origin_type origin_type; - enum config_scope scope; -}; - -extern NORETURN void git_die_config(const char *key, const char *err, ...) __attribute__((format(printf, 2, 3))); -extern NORETURN void git_die_config_linenr(const char *key, const char *filename, int linenr); - extern int committer_ident_sufficiently_given(void); extern int author_ident_sufficiently_given(void); @@@ -1967,8 -1907,7 +1966,8 @@@ extern int ws_blank_line(const char *li #define ws_tab_width(rule) ((rule) & WS_TAB_WIDTH_MASK) /* ls-files */ -void overlay_tree_on_cache(const char *tree_name, const char *prefix); +void overlay_tree_on_index(struct index_state *istate, + const char *tree_name, const char *prefix); char *alias_lookup(const char *alias); int split_cmdline(char *cmdline, const char ***argv); @@@ -1987,8 -1926,8 +1986,8 @@@ struct commit_list int try_merge_command(const char *strategy, size_t xopts_nr, const char **xopts, struct commit_list *common, const char *head_arg, struct commit_list *remotes); -int checkout_fast_forward(const unsigned char *from, - const unsigned char *to, +int checkout_fast_forward(const struct object_id *from, + const struct object_id *to, int overwrite_ignore); diff --combined sha1_file.c index 79feb1a305,fac860ad9b..189a1c3cdd --- a/sha1_file.c +++ b/sha1_file.c @@@ -7,7 -7,6 +7,7 @@@ * creation etc. */ #include "cache.h" +#include "config.h" #include "string-list.h" #include "lockfile.h" #include "delta.h" @@@ -27,7 -26,14 +27,7 @@@ #include "mru.h" #include "list.h" #include "mergesort.h" - -#ifndef O_NOATIME -#if defined(__linux__) && (defined(__i386__) || defined(__PPC__)) -#define O_NOATIME 01000000 -#else -#define O_NOATIME 0 -#endif -#endif +#include "quote.h" #define SZ_FMT PRIuMAX static inline uintmax_t sz_fmt(size_t s) { return s; } @@@ -130,10 -136,8 +130,10 @@@ enum scld_error safe_create_leading_dir *slash = '\0'; if (!stat(path, &st)) { /* path exists */ - if (!S_ISDIR(st.st_mode)) + if (!S_ISDIR(st.st_mode)) { + errno = ENOTDIR; ret = SCLD_EXISTS; + } } else if (mkdir(path, 0777)) { if (errno == EEXIST && !stat(path, &st) && S_ISDIR(st.st_mode)) @@@ -161,143 -165,70 +161,143 @@@ enum scld_error safe_create_leading_directories_const(const char *path) { + int save_errno; /* path points to cache entries, so xstrdup before messing with it */ char *buf = xstrdup(path); enum scld_error result = safe_create_leading_directories(buf); + + save_errno = errno; free(buf); + errno = save_errno; return result; } -static void fill_sha1_path(char *pathbuf, const unsigned char *sha1) +int raceproof_create_file(const char *path, create_file_fn fn, void *cb) +{ + /* + * The number of times we will try to remove empty directories + * in the way of path. This is only 1 because if another + * process is racily creating directories that conflict with + * us, we don't want to fight against them. + */ + int remove_directories_remaining = 1; + + /* + * The number of times that we will try to create the + * directories containing path. We are willing to attempt this + * more than once, because another process could be trying to + * clean up empty directories at the same time as we are + * trying to create them. + */ + int create_directories_remaining = 3; + + /* A scratch copy of path, filled lazily if we need it: */ + struct strbuf path_copy = STRBUF_INIT; + + int ret, save_errno; + + /* Sanity check: */ + assert(*path); + +retry_fn: + ret = fn(path, cb); + save_errno = errno; + if (!ret) + goto out; + + if (errno == EISDIR && remove_directories_remaining-- > 0) { + /* + * A directory is in the way. Maybe it is empty; try + * to remove it: + */ + if (!path_copy.len) + strbuf_addstr(&path_copy, path); + + if (!remove_dir_recursively(&path_copy, REMOVE_DIR_EMPTY_ONLY)) + goto retry_fn; + } else if (errno == ENOENT && create_directories_remaining-- > 0) { + /* + * Maybe the containing directory didn't exist, or + * maybe it was just deleted by a process that is + * racing with us to clean up empty directories. Try + * to create it: + */ + enum scld_error scld_result; + + if (!path_copy.len) + strbuf_addstr(&path_copy, path); + + do { + scld_result = safe_create_leading_directories(path_copy.buf); + if (scld_result == SCLD_OK) + goto retry_fn; + } while (scld_result == SCLD_VANISHED && create_directories_remaining-- > 0); + } + +out: + strbuf_release(&path_copy); + errno = save_errno; + return ret; +} + +static void fill_sha1_path(struct strbuf *buf, const unsigned char *sha1) { int i; for (i = 0; i < 20; i++) { static char hex[] = "0123456789abcdef"; unsigned int val = sha1[i]; - char *pos = pathbuf + i*2 + (i > 0); - *pos++ = hex[val >> 4]; - *pos = hex[val & 0xf]; + strbuf_addch(buf, hex[val >> 4]); + strbuf_addch(buf, hex[val & 0xf]); + if (!i) + strbuf_addch(buf, '/'); } } const char *sha1_file_name(const unsigned char *sha1) { - static char buf[PATH_MAX]; - const char *objdir; - int len; + static struct strbuf buf = STRBUF_INIT; - objdir = get_object_directory(); - len = strlen(objdir); + strbuf_reset(&buf); + strbuf_addf(&buf, "%s/", get_object_directory()); - /* '/' + sha1(2) + '/' + sha1(38) + '\0' */ - if (len + 43 > PATH_MAX) - die("insanely long object directory %s", objdir); - memcpy(buf, objdir, len); - buf[len] = '/'; - buf[len+3] = '/'; - buf[len+42] = '\0'; - fill_sha1_path(buf + len + 1, sha1); - return buf; + fill_sha1_path(&buf, sha1); + return buf.buf; } -/* - * Return the name of the pack or index file with the specified sha1 - * in its filename. *base and *name are scratch space that must be - * provided by the caller. which should be "pack" or "idx". - */ -static char *sha1_get_pack_name(const unsigned char *sha1, - struct strbuf *buf, - const char *which) +struct strbuf *alt_scratch_buf(struct alternate_object_database *alt) +{ + strbuf_setlen(&alt->scratch, alt->base_len); + return &alt->scratch; +} + +static const char *alt_sha1_path(struct alternate_object_database *alt, + const unsigned char *sha1) +{ + struct strbuf *buf = alt_scratch_buf(alt); + fill_sha1_path(buf, sha1); + return buf->buf; +} + + char *odb_pack_name(struct strbuf *buf, + const unsigned char *sha1, + const char *ext) { strbuf_reset(buf); strbuf_addf(buf, "%s/pack/pack-%s.%s", get_object_directory(), - sha1_to_hex(sha1), which); + sha1_to_hex(sha1), ext); return buf->buf; } char *sha1_pack_name(const unsigned char *sha1) { static struct strbuf buf = STRBUF_INIT; - return sha1_get_pack_name(sha1, &buf, "pack"); + return odb_pack_name(&buf, sha1, "pack"); } char *sha1_pack_index_name(const unsigned char *sha1) { static struct strbuf buf = STRBUF_INIT; - return sha1_get_pack_name(sha1, &buf, "idx"); + return odb_pack_name(&buf, sha1, "idx"); } struct alternate_object_database *alt_odb_list; @@@ -323,7 -254,8 +323,7 @@@ static int alt_odb_usable(struct strbu * thing twice, or object directory itself. */ for (alt = alt_odb_list; alt; alt = alt->next) { - if (path->len == alt->name - alt->base - 1 && - !memcmp(path->buf, alt->base, path->len)) + if (!fspathcmp(path->buf, alt->path)) return 0; } if (!fspathcmp(path->buf, normalized_objdir)) @@@ -347,19 -279,21 +347,20 @@@ * SHA1, an extra slash for the first level indirection, and the * terminating NUL. */ + static void read_info_alternates(const char * relative_base, int depth); static int link_alt_odb_entry(const char *entry, const char *relative_base, int depth, const char *normalized_objdir) { struct alternate_object_database *ent; - size_t entlen; struct strbuf pathbuf = STRBUF_INIT; if (!is_absolute_path(entry) && relative_base) { - strbuf_addstr(&pathbuf, real_path(relative_base)); + strbuf_realpath(&pathbuf, relative_base, 1); strbuf_addch(&pathbuf, '/'); } strbuf_addstr(&pathbuf, entry); - if (strbuf_normalize_path(&pathbuf) < 0) { + if (strbuf_normalize_path(&pathbuf) < 0 && relative_base) { error("unable to normalize alternate object path: %s", pathbuf.buf); strbuf_release(&pathbuf); @@@ -378,7 -312,14 +379,7 @@@ return -1; } - entlen = st_add(pathbuf.len, 43); /* '/' + 2 hex + '/' + 38 hex + NUL */ - ent = xmalloc(st_add(sizeof(*ent), entlen)); - memcpy(ent->base, pathbuf.buf, pathbuf.len); - - ent->name = ent->base + pathbuf.len + 1; - ent->base[pathbuf.len] = '/'; - ent->base[pathbuf.len + 3] = '/'; - ent->base[entlen-1] = 0; + ent = alloc_alt_odb(pathbuf.buf); /* add the alternate entry */ *alt_odb_tail = ent; @@@ -392,40 -333,13 +393,40 @@@ return 0; } +static const char *parse_alt_odb_entry(const char *string, + int sep, + struct strbuf *out) +{ + const char *end; + + strbuf_reset(out); + + if (*string == '#') { + /* comment; consume up to next separator */ + end = strchrnul(string, sep); + } else if (*string == '"' && !unquote_c_style(out, string, &end)) { + /* + * quoted path; unquote_c_style has copied the + * data for us and set "end". Broken quoting (e.g., + * an entry that doesn't end with a quote) falls + * back to the unquoted case below. + */ + } else { + /* normal, unquoted path */ + end = strchrnul(string, sep); + strbuf_add(out, string, end - string); + } + + if (*end) + end++; + return end; +} + static void link_alt_odb_entries(const char *alt, int len, int sep, const char *relative_base, int depth) { - struct string_list entries = STRING_LIST_INIT_NODUP; - char *alt_copy; - int i; struct strbuf objdirbuf = STRBUF_INIT; + struct strbuf entry = STRBUF_INIT; if (depth > 5) { error("%s: ignoring alternate object stores, nesting too deep.", @@@ -438,17 -352,25 +439,17 @@@ die("unable to normalize object directory: %s", objdirbuf.buf); - alt_copy = xmemdupz(alt, len); - string_list_split_in_place(&entries, alt_copy, sep, -1); - for (i = 0; i < entries.nr; i++) { - const char *entry = entries.items[i].string; - if (entry[0] == '\0' || entry[0] == '#') + while (*alt) { + alt = parse_alt_odb_entry(alt, sep, &entry); + if (!entry.len) continue; - if (!is_absolute_path(entry) && depth) { - error("%s: ignoring relative alternate object store %s", - relative_base, entry); - } else { - link_alt_odb_entry(entry, relative_base, depth, objdirbuf.buf); - } + link_alt_odb_entry(entry.buf, relative_base, depth, objdirbuf.buf); } - string_list_clear(&entries, 0); - free(alt_copy); + strbuf_release(&entry); strbuf_release(&objdirbuf); } - void read_info_alternates(const char * relative_base, int depth) + static void read_info_alternates(const char * relative_base, int depth) { char *map; size_t mapsz; @@@ -457,7 -379,7 +458,7 @@@ int fd; path = xstrfmt("%s/info/alternates", relative_base); - fd = git_open_noatime(path); + fd = git_open(path); free(path); if (fd < 0) return; @@@ -474,18 -396,6 +475,18 @@@ munmap(map, mapsz); } +struct alternate_object_database *alloc_alt_odb(const char *dir) +{ + struct alternate_object_database *ent; + + FLEX_ALLOC_STR(ent, path, dir); + strbuf_init(&ent->scratch, 0); + strbuf_addf(&ent->scratch, "%s/", dir); + ent->base_len = ent->scratch.len; + + return ent; +} + void add_to_alternates_file(const char *reference) { struct lock_file *lock = xcalloc(1, sizeof(struct lock_file)); @@@ -611,7 -521,8 +612,7 @@@ char *compute_alternate_path(const cha out: if (seen_error) { - free(ref_git); - ref_git = NULL; + FREE_AND_NULL(ref_git); } return ref_git; @@@ -662,7 -573,7 +663,7 @@@ static int freshen_file(const char *fn * either does not exist on disk, or has a stale mtime and may be subject to * pruning). */ -static int check_and_freshen_file(const char *fn, int freshen) +int check_and_freshen_file(const char *fn, int freshen) { if (access(fn, F_OK)) return 0; @@@ -681,8 -592,8 +682,8 @@@ static int check_and_freshen_nonlocal(c struct alternate_object_database *alt; prepare_alt_odb(); for (alt = alt_odb_list; alt; alt = alt->next) { - fill_sha1_path(alt->name, sha1); - if (check_and_freshen_file(alt->base, freshen)) + const char *path = alt_sha1_path(alt, sha1); + if (check_and_freshen_file(path, freshen)) return 1; } return 0; @@@ -749,7 -660,7 +750,7 @@@ static int check_packed_git_idx(const c struct pack_idx_header *hdr; size_t idx_size; uint32_t version, nr, i, *index; - int fd = git_open_noatime(path); + int fd = git_open(path); struct stat st; if (fd < 0) @@@ -1155,7 -1066,7 +1156,7 @@@ static int open_packed_git_1(struct pac while (pack_max_fds <= pack_open_fds && close_one_pack()) ; /* nothing */ - p->pack_fd = git_open_noatime(p->pack_name); + p->pack_fd = git_open(p->pack_name); if (p->pack_fd < 0 || fstat(p->pack_fd, &st)) return -1; pack_open_fds++; @@@ -1496,32 -1407,6 +1497,32 @@@ static void prepare_packed_git_one(cha strbuf_release(&path); } +static int approximate_object_count_valid; + +/* + * Give a fast, rough count of the number of objects in the repository. This + * ignores loose objects completely. If you have a lot of them, then either + * you should repack because your performance will be awful, or they are + * all unreachable objects about to be pruned, in which case they're not really + * interesting as a measure of repo size in the first place. + */ +unsigned long approximate_object_count(void) +{ + static unsigned long count; + if (!approximate_object_count_valid) { + struct packed_git *p; + + prepare_packed_git(); + count = 0; + for (p = packed_git; p; p = p->next) { + if (open_pack_index(p)) + continue; + count += p->num_objects; + } + } + return count; +} + static void *get_next_packed_git(const void *p) { return ((const struct packed_git *)p)->next; @@@ -1584,8 -1469,11 +1585,8 @@@ void prepare_packed_git(void return; prepare_packed_git_one(get_object_directory(), 1); prepare_alt_odb(); - for (alt = alt_odb_list; alt; alt = alt->next) { - alt->name[-1] = 0; - prepare_packed_git_one(alt->base, 0); - alt->name[-1] = '/'; - } + for (alt = alt_odb_list; alt; alt = alt->next) + prepare_packed_git_one(alt->path, 0); rearrange_packed_git(); prepare_packed_git_mru(); prepare_packed_git_run_once = 1; @@@ -1593,7 -1481,6 +1594,7 @@@ void reprepare_packed_git(void) { + approximate_object_count_valid = 0; prepare_packed_git_run_once = 0; prepare_packed_git(); } @@@ -1606,7 -1493,7 +1607,7 @@@ static void mark_bad_packed_object(stru if (!hashcmp(sha1, p->bad_object_sha1 + GIT_SHA1_RAWSZ * i)) return; p->bad_object_sha1 = xrealloc(p->bad_object_sha1, - st_mult(GIT_SHA1_RAWSZ, + st_mult(GIT_MAX_RAWSZ, st_add(p->num_bad_objects, 1))); hashcpy(p->bad_object_sha1 + GIT_SHA1_RAWSZ * p->num_bad_objects, sha1); p->num_bad_objects++; @@@ -1672,81 -1559,61 +1673,81 @@@ int check_sha1_signature(const unsigne return hashcmp(sha1, real_sha1) ? -1 : 0; } -int git_open_noatime(const char *name) +int git_open_cloexec(const char *name, int flags) { - static int sha1_file_open_flag = O_NOATIME; + int fd; + static int o_cloexec = O_CLOEXEC; - for (;;) { - int fd; + fd = open(name, flags | o_cloexec); + if ((o_cloexec & O_CLOEXEC) && fd < 0 && errno == EINVAL) { + /* Try again w/o O_CLOEXEC: the kernel might not support it */ + o_cloexec &= ~O_CLOEXEC; + fd = open(name, flags | o_cloexec); + } - errno = 0; - fd = open(name, O_RDONLY | sha1_file_open_flag); - if (fd >= 0) - return fd; +#if defined(F_GETFD) && defined(F_SETFD) && defined(FD_CLOEXEC) + { + static int fd_cloexec = FD_CLOEXEC; - /* Might the failure be due to O_NOATIME? */ - if (errno != ENOENT && sha1_file_open_flag) { - sha1_file_open_flag = 0; - continue; + if (!o_cloexec && 0 <= fd && fd_cloexec) { + /* Opened w/o O_CLOEXEC? try with fcntl(2) to add it */ + int flags = fcntl(fd, F_GETFD); + if (fcntl(fd, F_SETFD, flags | fd_cloexec)) + fd_cloexec = 0; } - - return -1; } +#endif + return fd; } -static int stat_sha1_file(const unsigned char *sha1, struct stat *st) +/* + * Find "sha1" as a loose object in the local repository or in an alternate. + * Returns 0 on success, negative on failure. + * + * The "path" out-parameter will give the path of the object we found (if any). + * Note that it may point to static storage and is only valid until another + * call to sha1_file_name(), etc. + */ +static int stat_sha1_file(const unsigned char *sha1, struct stat *st, + const char **path) { struct alternate_object_database *alt; - if (!lstat(sha1_file_name(sha1), st)) + *path = sha1_file_name(sha1); + if (!lstat(*path, st)) return 0; prepare_alt_odb(); errno = ENOENT; for (alt = alt_odb_list; alt; alt = alt->next) { - fill_sha1_path(alt->name, sha1); - if (!lstat(alt->base, st)) + *path = alt_sha1_path(alt, sha1); + if (!lstat(*path, st)) return 0; } return -1; } -static int open_sha1_file(const unsigned char *sha1) +/* + * Like stat_sha1_file(), but actually open the object and return the + * descriptor. See the caveats on the "path" parameter above. + */ +static int open_sha1_file(const unsigned char *sha1, const char **path) { int fd; struct alternate_object_database *alt; int most_interesting_errno; - fd = git_open_noatime(sha1_file_name(sha1)); + *path = sha1_file_name(sha1); + fd = git_open(*path); if (fd >= 0) return fd; most_interesting_errno = errno; prepare_alt_odb(); for (alt = alt_odb_list; alt; alt = alt->next) { - fill_sha1_path(alt->name, sha1); - fd = git_open_noatime(alt->base); + *path = alt_sha1_path(alt, sha1); + fd = git_open(*path); if (fd >= 0) return fd; if (most_interesting_errno == ENOENT) @@@ -1756,21 -1623,12 +1757,21 @@@ return -1; } -void *map_sha1_file(const unsigned char *sha1, unsigned long *size) +/* + * Map the loose object at "path" if it is not NULL, or the path found by + * searching for a loose object named "sha1". + */ +static void *map_sha1_file_1(const char *path, + const unsigned char *sha1, + unsigned long *size) { void *map; int fd; - fd = open_sha1_file(sha1); + if (path) + fd = git_open(path); + else + fd = open_sha1_file(sha1, &path); map = NULL; if (fd >= 0) { struct stat st; @@@ -1779,7 -1637,7 +1780,7 @@@ *size = xsize_t(st.st_size); if (!*size) { /* mmap() is forbidden on empty files */ - error("object file %s is empty", sha1_file_name(sha1)); + error("object file %s is empty", path); return NULL; } map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0); @@@ -1789,11 -1647,6 +1790,11 @@@ return map; } +void *map_sha1_file(const unsigned char *sha1, unsigned long *size) +{ + return map_sha1_file_1(NULL, sha1, size); +} + unsigned long unpack_object_header_buffer(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep) { @@@ -1964,7 -1817,7 +1965,7 @@@ static int parse_sha1_header_extended(c * we're obtaining the type using '--allow-unknown-type' * option. */ - if ((flags & LOOKUP_UNKNOWN_OBJECT) && (type < 0)) + if ((flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE) && (type < 0)) type = 0; else if (type < 0) die("invalid object type"); @@@ -1999,10 -1852,25 +2000,10 @@@ int parse_sha1_header(const char *hdr, unsigned long *sizep) { - struct object_info oi; + struct object_info oi = OBJECT_INFO_INIT; oi.sizep = sizep; - oi.typename = NULL; - oi.typep = NULL; - return parse_sha1_header_extended(hdr, &oi, LOOKUP_REPLACE_OBJECT); -} - -static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1) -{ - int ret; - git_zstream stream; - char hdr[8192]; - - ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)); - if (ret < Z_OK || (*type = parse_sha1_header(hdr, size)) < 0) - return NULL; - - return unpack_sha1_rest(&stream, hdr, *size, sha1); + return parse_sha1_header_extended(hdr, &oi, 0); } unsigned long get_size_from_delta(struct packed_git *p, @@@ -2226,6 -2094,107 +2227,6 @@@ unwind goto out; } -static int packed_object_info(struct packed_git *p, off_t obj_offset, - struct object_info *oi) -{ - struct pack_window *w_curs = NULL; - unsigned long size; - off_t curpos = obj_offset; - enum object_type type; - - /* - * We always get the representation type, but only convert it to - * a "real" type later if the caller is interested. - */ - type = unpack_object_header(p, &w_curs, &curpos, &size); - - if (oi->sizep) { - if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { - off_t tmp_pos = curpos; - off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos, - type, obj_offset); - if (!base_offset) { - type = OBJ_BAD; - goto out; - } - *oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos); - if (*oi->sizep == 0) { - type = OBJ_BAD; - goto out; - } - } else { - *oi->sizep = size; - } - } - - if (oi->disk_sizep) { - struct revindex_entry *revidx = find_pack_revindex(p, obj_offset); - *oi->disk_sizep = revidx[1].offset - obj_offset; - } - - if (oi->typep) { - *oi->typep = packed_to_object_type(p, obj_offset, type, &w_curs, curpos); - if (*oi->typep < 0) { - type = OBJ_BAD; - goto out; - } - } - - if (oi->delta_base_sha1) { - if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { - const unsigned char *base; - - base = get_delta_base_sha1(p, &w_curs, curpos, - type, obj_offset); - if (!base) { - type = OBJ_BAD; - goto out; - } - - hashcpy(oi->delta_base_sha1, base); - } else - hashclr(oi->delta_base_sha1); - } - -out: - unuse_pack(&w_curs); - return type; -} - -static void *unpack_compressed_entry(struct packed_git *p, - struct pack_window **w_curs, - off_t curpos, - unsigned long size) -{ - int st; - git_zstream stream; - unsigned char *buffer, *in; - - buffer = xmallocz_gently(size); - if (!buffer) - return NULL; - memset(&stream, 0, sizeof(stream)); - stream.next_out = buffer; - stream.avail_out = size + 1; - - git_inflate_init(&stream); - do { - in = use_pack(p, w_curs, curpos, &stream.avail_in); - stream.next_in = in; - st = git_inflate(&stream, Z_FINISH); - if (!stream.avail_out) - break; /* the payload is larger than it should be */ - curpos += stream.next_in - in; - } while (st == Z_OK || st == Z_BUF_ERROR); - git_inflate_end(&stream); - if ((st != Z_STREAM_END) || stream.total_out != size) { - free(buffer); - return NULL; - } - - return buffer; -} - static struct hashmap delta_base_cache; static size_t delta_base_cached; @@@ -2275,8 -2244,7 +2276,8 @@@ static int delta_base_cache_key_eq(cons return a->p == b->p && a->base_offset == b->base_offset; } -static int delta_base_cache_hash_cmp(const void *va, const void *vb, +static int delta_base_cache_hash_cmp(const void *unused_cmp_data, + const void *va, const void *vb, const void *vkey) { const struct delta_base_cache_entry *a = va, *b = vb; @@@ -2314,10 -2282,8 +2315,10 @@@ static void *cache_or_unpack_entry(stru if (!ent) return unpack_entry(p, base_offset, type, base_size); - *type = ent->type; - *base_size = ent->size; + if (type) + *type = ent->type; + if (base_size) + *base_size = ent->size; return xmemdupz(ent->data, ent->size); } @@@ -2329,10 -2295,11 +2330,10 @@@ static inline void release_delta_base_c void clear_delta_base_cache(void) { - struct hashmap_iter iter; - struct delta_base_cache_entry *entry; - for (entry = hashmap_iter_first(&delta_base_cache, &iter); - entry; - entry = hashmap_iter_next(&iter)) { + struct list_head *lru, *tmp; + list_for_each_safe(lru, tmp, &delta_base_cache_lru) { + struct delta_base_cache_entry *entry = + list_entry(lru, struct delta_base_cache_entry, lru); release_delta_base_cache(entry); } } @@@ -2361,131 -2328,11 +2362,131 @@@ static void add_delta_base_cache(struc list_add_tail(&ent->lru, &delta_base_cache_lru); if (!delta_base_cache.cmpfn) - hashmap_init(&delta_base_cache, delta_base_cache_hash_cmp, 0); + hashmap_init(&delta_base_cache, delta_base_cache_hash_cmp, NULL, 0); hashmap_entry_init(ent, pack_entry_hash(p, base_offset)); hashmap_add(&delta_base_cache, ent); } +int packed_object_info(struct packed_git *p, off_t obj_offset, + struct object_info *oi) +{ + struct pack_window *w_curs = NULL; + unsigned long size; + off_t curpos = obj_offset; + enum object_type type; + + /* + * We always get the representation type, but only convert it to + * a "real" type later if the caller is interested. + */ + if (oi->contentp) { + *oi->contentp = cache_or_unpack_entry(p, obj_offset, oi->sizep, + &type); + if (!*oi->contentp) + type = OBJ_BAD; + } else { + type = unpack_object_header(p, &w_curs, &curpos, &size); + } + + if (!oi->contentp && oi->sizep) { + if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { + off_t tmp_pos = curpos; + off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos, + type, obj_offset); + if (!base_offset) { + type = OBJ_BAD; + goto out; + } + *oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos); + if (*oi->sizep == 0) { + type = OBJ_BAD; + goto out; + } + } else { + *oi->sizep = size; + } + } + + if (oi->disk_sizep) { + struct revindex_entry *revidx = find_pack_revindex(p, obj_offset); + *oi->disk_sizep = revidx[1].offset - obj_offset; + } + + if (oi->typep || oi->typename) { + enum object_type ptot; + ptot = packed_to_object_type(p, obj_offset, type, &w_curs, + curpos); + if (oi->typep) + *oi->typep = ptot; + if (oi->typename) { + const char *tn = typename(ptot); + if (tn) + strbuf_addstr(oi->typename, tn); + } + if (ptot < 0) { + type = OBJ_BAD; + goto out; + } + } + + if (oi->delta_base_sha1) { + if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { + const unsigned char *base; + + base = get_delta_base_sha1(p, &w_curs, curpos, + type, obj_offset); + if (!base) { + type = OBJ_BAD; + goto out; + } + + hashcpy(oi->delta_base_sha1, base); + } else + hashclr(oi->delta_base_sha1); + } + + oi->whence = in_delta_base_cache(p, obj_offset) ? OI_DBCACHED : + OI_PACKED; + +out: + unuse_pack(&w_curs); + return type; +} + +static void *unpack_compressed_entry(struct packed_git *p, + struct pack_window **w_curs, + off_t curpos, + unsigned long size) +{ + int st; + git_zstream stream; + unsigned char *buffer, *in; + + buffer = xmallocz_gently(size); + if (!buffer) + return NULL; + memset(&stream, 0, sizeof(stream)); + stream.next_out = buffer; + stream.avail_out = size + 1; + + git_inflate_init(&stream); + do { + in = use_pack(p, w_curs, curpos, &stream.avail_in); + stream.next_in = in; + st = git_inflate(&stream, Z_FINISH); + if (!stream.avail_out) + break; /* the payload is larger than it should be */ + curpos += stream.next_in - in; + } while (st == Z_OK || st == Z_BUF_ERROR); + git_inflate_end(&stream); + if ((st != Z_STREAM_END) || stream.total_out != size) { + free(buffer); + return NULL; + } + + return buffer; +} + static void *read_object(const unsigned char *sha1, enum object_type *type, unsigned long *size); @@@ -2545,8 -2392,8 +2546,8 @@@ void *unpack_entry(struct packed_git *p error("bad packed object CRC for %s", sha1_to_hex(sha1)); mark_bad_packed_object(p, sha1); - unuse_pack(&w_curs); - return NULL; + data = NULL; + goto out; } } @@@ -2610,7 -2457,6 +2611,7 @@@ while (delta_stack_nr) { void *delta_data; void *base = data; + void *external_base = NULL; unsigned long delta_size, base_size = size; int i; @@@ -2637,7 -2483,6 +2638,7 @@@ p->pack_name); mark_bad_packed_object(p, base_sha1); base = read_object(base_sha1, &type, &base_size); + external_base = base; } } @@@ -2656,7 -2501,6 +2657,7 @@@ "at offset %"PRIuMAX" from %s", (uintmax_t)curpos, p->pack_name); data = NULL; + free(external_base); continue; } @@@ -2676,15 -2520,11 +2677,15 @@@ error("failed to apply delta"); free(delta_data); + free(external_base); } - *final_type = type; - *final_size = size; + if (final_type) + *final_type = type; + if (final_size) + *final_size = size; +out: unuse_pack(&w_curs); if (delta_stack != small_delta_stack) @@@ -2713,17 -2553,6 +2714,17 @@@ const unsigned char *nth_packed_object_ } } +const struct object_id *nth_packed_object_oid(struct object_id *oid, + struct packed_git *p, + uint32_t n) +{ + const unsigned char *hash = nth_packed_object_sha1(p, n); + if (!hash) + return NULL; + hashcpy(oid->hash, hash); + return oid; +} + void check_pack_index_ptr(const struct packed_git *p, const void *vptr) { const unsigned char *ptr = vptr; @@@ -2763,6 -2592,7 +2764,6 @@@ off_t find_pack_entry_one(const unsigne const uint32_t *level1_ofs = p->index_data; const unsigned char *index = p->index_data; unsigned hi, lo, stride; - static int use_lookup = -1; static int debug_lookup = -1; if (debug_lookup < 0) @@@ -2792,7 -2622,17 +2793,7 @@@ printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n", sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects); - if (use_lookup < 0) - use_lookup = !!getenv("GIT_USE_LOOKUP"); - if (use_lookup) { - int pos = sha1_entry_pos(index, stride, 0, - lo, hi, p->num_objects, sha1); - if (pos < 0) - return 0; - return nth_packed_object_offset(p, pos); - } - - do { + while (lo < hi) { unsigned mi = (lo + hi) / 2; int cmp = hashcmp(index + mi * stride, sha1); @@@ -2805,7 -2645,7 +2806,7 @@@ hi = mi; else lo = mi+1; - } while (lo < hi); + } return 0; } @@@ -2906,7 -2746,6 +2907,7 @@@ static int sha1_loose_object_info(cons git_zstream stream; char hdr[32]; struct strbuf hdrbuf = STRBUF_INIT; + unsigned long size_scratch; if (oi->delta_base_sha1) hashclr(oi->delta_base_sha1); @@@ -2919,10 -2758,9 +2920,10 @@@ * return value implicitly indicates whether the * object even exists. */ - if (!oi->typep && !oi->typename && !oi->sizep) { + if (!oi->typep && !oi->typename && !oi->sizep && !oi->contentp) { + const char *path; struct stat st; - if (stat_sha1_file(sha1, &st) < 0) + if (stat_sha1_file(sha1, &st, &path) < 0) return -1; if (oi->disk_sizep) *oi->disk_sizep = st.st_size; @@@ -2932,13 -2770,9 +2933,13 @@@ map = map_sha1_file(sha1, &mapsize); if (!map) return -1; + + if (!oi->sizep) + oi->sizep = &size_scratch; + if (oi->disk_sizep) *oi->disk_sizep = mapsize; - if ((flags & LOOKUP_UNKNOWN_OBJECT)) { + if ((flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE)) { if (unpack_sha1_header_to_strbuf(&stream, map, mapsize, hdr, sizeof(hdr), &hdrbuf) < 0) status = error("unable to unpack %s header with --allow-unknown-type", sha1_to_hex(sha1)); @@@ -2953,87 -2787,77 +2954,87 @@@ sha1_to_hex(sha1)); } else if ((status = parse_sha1_header_extended(hdr, oi, flags)) < 0) status = error("unable to parse %s header", sha1_to_hex(sha1)); - git_inflate_end(&stream); + + if (status >= 0 && oi->contentp) + *oi->contentp = unpack_sha1_rest(&stream, hdr, + *oi->sizep, sha1); + else + git_inflate_end(&stream); + munmap(map, mapsize); if (status && oi->typep) *oi->typep = status; + if (oi->sizep == &size_scratch) + oi->sizep = NULL; strbuf_release(&hdrbuf); - return 0; + oi->whence = OI_LOOSE; + return (status < 0) ? status : 0; } int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi, unsigned flags) { - struct cached_object *co; + static struct object_info blank_oi = OBJECT_INFO_INIT; struct pack_entry e; int rtype; - enum object_type real_type; - const unsigned char *real = lookup_replace_object_extended(sha1, flags); - - co = find_cached_object(real); - if (co) { - if (oi->typep) - *(oi->typep) = co->type; - if (oi->sizep) - *(oi->sizep) = co->size; - if (oi->disk_sizep) - *(oi->disk_sizep) = 0; - if (oi->delta_base_sha1) - hashclr(oi->delta_base_sha1); - if (oi->typename) - strbuf_addstr(oi->typename, typename(co->type)); - oi->whence = OI_CACHED; - return 0; + const unsigned char *real = (flags & OBJECT_INFO_LOOKUP_REPLACE) ? + lookup_replace_object(sha1) : + sha1; + + if (!oi) + oi = &blank_oi; + + if (!(flags & OBJECT_INFO_SKIP_CACHED)) { + struct cached_object *co = find_cached_object(real); + if (co) { + if (oi->typep) + *(oi->typep) = co->type; + if (oi->sizep) + *(oi->sizep) = co->size; + if (oi->disk_sizep) + *(oi->disk_sizep) = 0; + if (oi->delta_base_sha1) + hashclr(oi->delta_base_sha1); + if (oi->typename) + strbuf_addstr(oi->typename, typename(co->type)); + if (oi->contentp) + *oi->contentp = xmemdupz(co->buf, co->size); + oi->whence = OI_CACHED; + return 0; + } } if (!find_pack_entry(real, &e)) { /* Most likely it's a loose object. */ - if (!sha1_loose_object_info(real, oi, flags)) { - oi->whence = OI_LOOSE; + if (!sha1_loose_object_info(real, oi, flags)) return 0; - } /* Not a loose object; someone else may have just packed it. */ - reprepare_packed_git(); - if (!find_pack_entry(real, &e)) + if (flags & OBJECT_INFO_QUICK) { return -1; + } else { + reprepare_packed_git(); + if (!find_pack_entry(real, &e)) + return -1; + } } - /* - * packed_object_info() does not follow the delta chain to - * find out the real type, unless it is given oi->typep. - */ - if (oi->typename && !oi->typep) - oi->typep = &real_type; + if (oi == &blank_oi) + /* + * We know that the caller doesn't actually need the + * information below, so return early. + */ + return 0; rtype = packed_object_info(e.p, e.offset, oi); if (rtype < 0) { mark_bad_packed_object(e.p, real); - if (oi->typep == &real_type) - oi->typep = NULL; return sha1_object_info_extended(real, oi, 0); - } else if (in_delta_base_cache(e.p, e.offset)) { - oi->whence = OI_DBCACHED; - } else { - oi->whence = OI_PACKED; + } else if (oi->whence == OI_PACKED) { oi->u.packed.offset = e.offset; oi->u.packed.pack = e.p; oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA || rtype == OBJ_OFS_DELTA); } - if (oi->typename) - strbuf_addstr(oi->typename, typename(*oi->typep)); - if (oi->typep == &real_type) - oi->typep = NULL; return 0; } @@@ -3042,16 -2866,39 +3043,16 @@@ int sha1_object_info(const unsigned char *sha1, unsigned long *sizep) { enum object_type type; - struct object_info oi = {NULL}; + struct object_info oi = OBJECT_INFO_INIT; oi.typep = &type; oi.sizep = sizep; - if (sha1_object_info_extended(sha1, &oi, LOOKUP_REPLACE_OBJECT) < 0) + if (sha1_object_info_extended(sha1, &oi, + OBJECT_INFO_LOOKUP_REPLACE) < 0) return -1; return type; } -static void *read_packed_sha1(const unsigned char *sha1, - enum object_type *type, unsigned long *size) -{ - struct pack_entry e; - void *data; - - if (!find_pack_entry(sha1, &e)) - return NULL; - data = cache_or_unpack_entry(e.p, e.offset, size, type); - if (!data) { - /* - * We're probably in deep shit, but let's try to fetch - * the required object anyway from another pack or loose. - * This should happen only in the presence of a corrupted - * pack, and is better than failing outright. - */ - error("failed to read object %s at offset %"PRIuMAX" from %s", - sha1_to_hex(sha1), (uintmax_t)e.offset, e.p->pack_name); - mark_bad_packed_object(e.p, sha1); - data = read_object(sha1, type, size); - } - return data; -} - int pretend_sha1_file(void *buf, unsigned long len, enum object_type type, unsigned char *sha1) { @@@ -3073,15 -2920,28 +3074,15 @@@ static void *read_object(const unsigned char *sha1, enum object_type *type, unsigned long *size) { - unsigned long mapsize; - void *map, *buf; - struct cached_object *co; + struct object_info oi = OBJECT_INFO_INIT; + void *content; + oi.typep = type; + oi.sizep = size; + oi.contentp = &content; - co = find_cached_object(sha1); - if (co) { - *type = co->type; - *size = co->size; - return xmemdupz(co->buf, co->size); - } - - buf = read_packed_sha1(sha1, type, size); - if (buf) - return buf; - map = map_sha1_file(sha1, &mapsize); - if (map) { - buf = unpack_sha1_file(map, mapsize, type, size, sha1); - munmap(map, mapsize); - return buf; - } - reprepare_packed_git(); - return read_packed_sha1(sha1, type, size); + if (sha1_object_info_extended(sha1, &oi, 0) < 0) + return NULL; + return content; } /* @@@ -3092,14 -2952,11 +3093,14 @@@ void *read_sha1_file_extended(const unsigned char *sha1, enum object_type *type, unsigned long *size, - unsigned flag) + int lookup_replace) { void *data; const struct packed_git *p; - const unsigned char *repl = lookup_replace_object_extended(sha1, flag); + const char *path; + struct stat st; + const unsigned char *repl = lookup_replace ? lookup_replace_object(sha1) + : sha1; errno = 0; data = read_object(repl, type, size); @@@ -3114,9 -2971,12 +3115,9 @@@ die("replacement %s not found for %s", sha1_to_hex(repl), sha1_to_hex(sha1)); - if (has_loose_object(repl)) { - const char *path = sha1_file_name(sha1); - + if (!stat_sha1_file(repl, &st, &path)) die("loose object %s (stored in %s) is corrupt", sha1_to_hex(repl), path); - } if ((p = has_packed_and_bad(repl)) != NULL) die("packed object %s (stored in %s) is corrupt", @@@ -3434,7 -3294,7 +3435,7 @@@ int force_object_loose(const unsigned c if (has_loose_object(sha1)) return 0; - buf = read_packed_sha1(sha1, &type, &len); + buf = read_object(sha1, &type, &len); if (!buf) return error("cannot read sha1_file for %s", sha1_to_hex(sha1)); hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(type), len) + 1; @@@ -3460,10 -3320,16 +3461,10 @@@ int has_sha1_pack(const unsigned char * int has_sha1_file_with_flags(const unsigned char *sha1, int flags) { - struct pack_entry e; - - if (find_pack_entry(sha1, &e)) - return 1; - if (has_loose_object(sha1)) - return 1; - if (flags & HAS_SHA1_QUICK) + if (!startup_info->have_repository) return 0; - reprepare_packed_git(); - return find_pack_entry(sha1, &e); + return sha1_object_info_extended(sha1, NULL, + flags | OBJECT_INFO_SKIP_CACHED) >= 0; } int has_object_file(const struct object_id *oid) @@@ -3471,11 -3337,6 +3472,11 @@@ return has_sha1_file(oid->hash); } +int has_object_file_with_flags(const struct object_id *oid, int flags) +{ + return has_sha1_file_with_flags(oid->hash, flags); +} + static void check_tree(const void *buf, size_t size) { struct tree_desc desc; @@@ -3519,7 -3380,7 +3520,7 @@@ static int index_mem(unsigned char *sha */ if ((type == OBJ_BLOB) && path) { struct strbuf nbuf = STRBUF_INIT; - if (convert_to_git(path, buf, size, &nbuf, + if (convert_to_git(&the_index, path, buf, size, &nbuf, write_object ? safe_crlf : SAFE_CRLF_FALSE)) { buf = strbuf_detach(&nbuf, &size); re_allocated = 1; @@@ -3553,7 -3414,7 +3554,7 @@@ static int index_stream_convert_blob(un assert(path); assert(would_convert_to_git_filter_fd(path)); - convert_to_git_filter_fd(path, fd, &sbuf, + convert_to_git_filter_fd(&the_index, path, fd, &sbuf, write_object ? safe_crlf : SAFE_CRLF_FALSE); if (write_object) @@@ -3641,7 -3502,7 +3642,7 @@@ int index_fd(unsigned char *sha1, int f else if (!S_ISREG(st->st_mode)) ret = index_pipe(sha1, fd, type, path, flags); else if (st->st_size <= big_file_threshold || type != OBJ_BLOB || - (path && would_convert_to_git(path))) + (path && would_convert_to_git(&the_index, path))) ret = index_core(sha1, fd, xsize_t(st->st_size), type, path, flags); else @@@ -3708,32 -3569,22 +3709,32 @@@ void assert_sha1_type(const unsigned ch typename(expect)); } -static int for_each_file_in_obj_subdir(int subdir_nr, - struct strbuf *path, - each_loose_object_fn obj_cb, - each_loose_cruft_fn cruft_cb, - each_loose_subdir_fn subdir_cb, - void *data) +int for_each_file_in_obj_subdir(unsigned int subdir_nr, + struct strbuf *path, + each_loose_object_fn obj_cb, + each_loose_cruft_fn cruft_cb, + each_loose_subdir_fn subdir_cb, + void *data) { - size_t baselen = path->len; - DIR *dir = opendir(path->buf); + size_t origlen, baselen; + DIR *dir; struct dirent *de; int r = 0; + if (subdir_nr > 0xff) + BUG("invalid loose object subdirectory: %x", subdir_nr); + + origlen = path->len; + strbuf_complete(path, '/'); + strbuf_addf(path, "%02x", subdir_nr); + baselen = path->len; + + dir = opendir(path->buf); if (!dir) { - if (errno == ENOENT) - return 0; - return error_errno("unable to open %s", path->buf); + if (errno != ENOENT) + r = error_errno("unable to open %s", path->buf); + strbuf_setlen(path, origlen); + return r; } while ((de = readdir(dir))) { @@@ -3743,15 -3594,15 +3744,15 @@@ strbuf_setlen(path, baselen); strbuf_addf(path, "/%s", de->d_name); - if (strlen(de->d_name) == 38) { - char hex[41]; - unsigned char sha1[20]; + if (strlen(de->d_name) == GIT_SHA1_HEXSZ - 2) { + char hex[GIT_MAX_HEXSZ+1]; + struct object_id oid; - snprintf(hex, sizeof(hex), "%02x%s", - subdir_nr, de->d_name); - if (!get_sha1_hex(hex, sha1)) { + xsnprintf(hex, sizeof(hex), "%02x%s", + subdir_nr, de->d_name); + if (!get_oid_hex(hex, &oid)) { if (obj_cb) { - r = obj_cb(sha1, path->buf, data); + r = obj_cb(&oid, path->buf, data); if (r) break; } @@@ -3771,8 -3622,6 +3772,8 @@@ if (!r && subdir_cb) r = subdir_cb(subdir_nr, path->buf, data); + strbuf_setlen(path, origlen); + return r; } @@@ -3782,12 -3631,15 +3783,12 @@@ int for_each_loose_file_in_objdir_buf(s each_loose_subdir_fn subdir_cb, void *data) { - size_t baselen = path->len; int r = 0; int i; for (i = 0; i < 256; i++) { - strbuf_addf(path, "/%02x", i); r = for_each_file_in_obj_subdir(i, path, obj_cb, cruft_cb, subdir_cb, data); - strbuf_setlen(path, baselen); if (r) break; } @@@ -3824,7 -3676,8 +3825,7 @@@ static int loose_from_alt_odb(struct al struct strbuf buf = STRBUF_INIT; int r; - /* copy base not including trailing '/' */ - strbuf_add(&buf, alt->base, alt->name - alt->base - 1); + strbuf_addstr(&buf, alt->path); r = for_each_loose_file_in_objdir_buf(&buf, data->cb, NULL, NULL, data->data); @@@ -3856,13 -3709,13 +3857,13 @@@ static int for_each_object_in_pack(stru int r = 0; for (i = 0; i < p->num_objects; i++) { - const unsigned char *sha1 = nth_packed_object_sha1(p, i); + struct object_id oid; - if (!sha1) + if (!nth_packed_object_oid(&oid, p, i)) return error("unable to get sha1 of object %u in %s", i, p->pack_name); - r = cb(sha1, p, i, data); + r = cb(&oid, p, i, data); if (r) break; } @@@ -3889,119 -3742,3 +3890,119 @@@ int for_each_packed_object(each_packed_ } return r ? r : pack_errors; } + +static int check_stream_sha1(git_zstream *stream, + const char *hdr, + unsigned long size, + const char *path, + const unsigned char *expected_sha1) +{ + git_SHA_CTX c; + unsigned char real_sha1[GIT_MAX_RAWSZ]; + unsigned char buf[4096]; + unsigned long total_read; + int status = Z_OK; + + git_SHA1_Init(&c); + git_SHA1_Update(&c, hdr, stream->total_out); + + /* + * We already read some bytes into hdr, but the ones up to the NUL + * do not count against the object's content size. + */ + total_read = stream->total_out - strlen(hdr) - 1; + + /* + * This size comparison must be "<=" to read the final zlib packets; + * see the comment in unpack_sha1_rest for details. + */ + while (total_read <= size && + (status == Z_OK || status == Z_BUF_ERROR)) { + stream->next_out = buf; + stream->avail_out = sizeof(buf); + if (size - total_read < stream->avail_out) + stream->avail_out = size - total_read; + status = git_inflate(stream, Z_FINISH); + git_SHA1_Update(&c, buf, stream->next_out - buf); + total_read += stream->next_out - buf; + } + git_inflate_end(stream); + + if (status != Z_STREAM_END) { + error("corrupt loose object '%s'", sha1_to_hex(expected_sha1)); + return -1; + } + if (stream->avail_in) { + error("garbage at end of loose object '%s'", + sha1_to_hex(expected_sha1)); + return -1; + } + + git_SHA1_Final(real_sha1, &c); + if (hashcmp(expected_sha1, real_sha1)) { + error("sha1 mismatch for %s (expected %s)", path, + sha1_to_hex(expected_sha1)); + return -1; + } + + return 0; +} + +int read_loose_object(const char *path, + const unsigned char *expected_sha1, + enum object_type *type, + unsigned long *size, + void **contents) +{ + int ret = -1; + void *map = NULL; + unsigned long mapsize; + git_zstream stream; + char hdr[32]; + + *contents = NULL; + + map = map_sha1_file_1(path, NULL, &mapsize); + if (!map) { + error_errno("unable to mmap %s", path); + goto out; + } + + if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0) { + error("unable to unpack header of %s", path); + goto out; + } + + *type = parse_sha1_header(hdr, size); + if (*type < 0) { + error("unable to parse header of %s", path); + git_inflate_end(&stream); + goto out; + } + + if (*type == OBJ_BLOB) { + if (check_stream_sha1(&stream, hdr, *size, path, expected_sha1) < 0) + goto out; + } else { + *contents = unpack_sha1_rest(&stream, hdr, *size, expected_sha1); + if (!*contents) { + error("unable to unpack contents of %s", path); + git_inflate_end(&stream); + goto out; + } + if (check_sha1_signature(expected_sha1, *contents, + *size, typename(*type))) { + error("sha1 mismatch for %s (expected %s)", path, + sha1_to_hex(expected_sha1)); + free(*contents); + goto out; + } + } + + ret = 0; /* everything checks out */ + +out: + if (map) + munmap(map, mapsize); + return ret; +}