From: Jeff King Date: Fri, 20 Nov 2015 11:55:34 +0000 (-0500) Subject: Merge branch 'dk/gc-idx-wo-pack' X-Git-Tag: v2.7.0-rc0~33 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/45014beac004a610938a265698605c18ab126087?ds=inline;hp=-c Merge branch 'dk/gc-idx-wo-pack' Having a leftover .idx file without corresponding .pack file in the repository hurts performance; "git gc" learned to prune them. * dk/gc-idx-wo-pack: gc: remove garbage .idx files from pack dir t5304: test cleaning pack garbage prepare_packed_git(): refactor garbage reporting in pack directory --- 45014beac004a610938a265698605c18ab126087 diff --combined builtin/gc.c index df3e454447,203265db76..c583aad6ec --- a/builtin/gc.c +++ b/builtin/gc.c @@@ -11,7 -11,6 +11,7 @@@ */ #include "builtin.h" +#include "tempfile.h" #include "lockfile.h" #include "parse-options.h" #include "run-command.h" @@@ -43,9 -42,37 +43,25 @@@ static struct argv_array prune = ARGV_A static struct argv_array prune_worktrees = ARGV_ARRAY_INIT; static struct argv_array rerere = ARGV_ARRAY_INIT; -static char *pidfile; - -static void remove_pidfile(void) -{ - if (pidfile) - unlink(pidfile); -} - -static void remove_pidfile_on_signal(int signo) -{ - remove_pidfile(); - sigchain_pop(signo); - raise(signo); -} +static struct tempfile pidfile; +static struct lock_file log_lock; + static struct string_list pack_garbage = STRING_LIST_INIT_DUP; + + static void clean_pack_garbage(void) + { + int i; + for (i = 0; i < pack_garbage.nr; i++) + unlink_or_warn(pack_garbage.items[i].string); + string_list_clear(&pack_garbage, 0); + } + + static void report_pack_garbage(unsigned seen_bits, const char *path) + { + if (seen_bits == PACKDIR_FILE_IDX) + string_list_append(&pack_garbage, path); + } + static void git_config_date_string(const char *key, const char **output) { if (git_config_get_string_const(key, output)) @@@ -57,28 -84,6 +73,28 @@@ } } +static void process_log_file(void) +{ + struct stat st; + if (!fstat(get_lock_file_fd(&log_lock), &st) && st.st_size) + commit_lock_file(&log_lock); + else + rollback_lock_file(&log_lock); +} + +static void process_log_file_at_exit(void) +{ + fflush(stderr); + process_log_file(); +} + +static void process_log_file_on_signal(int signo) +{ + process_log_file(); + sigchain_pop(signo); + raise(signo); +} + static void gc_config(void) { const char *value; @@@ -96,7 -101,7 +112,7 @@@ git_config_get_int("gc.autopacklimit", &gc_auto_pack_limit); git_config_get_bool("gc.autodetach", &detach_auto); git_config_date_string("gc.pruneexpire", &prune_expire); - git_config_date_string("gc.pruneworktreesexpire", &prune_worktrees_expire); + git_config_date_string("gc.worktreepruneexpire", &prune_worktrees_expire); git_config(git_default_config, NULL); } @@@ -210,22 -215,20 +226,22 @@@ static const char *lock_repo_for_gc(in uintmax_t pid; FILE *fp; int fd; + char *pidfile_path; - if (pidfile) + if (is_tempfile_active(&pidfile)) /* already locked */ return NULL; if (gethostname(my_host, sizeof(my_host))) - strcpy(my_host, "unknown"); + xsnprintf(my_host, sizeof(my_host), "unknown"); - fd = hold_lock_file_for_update(&lock, git_path("gc.pid"), + pidfile_path = git_pathdup("gc.pid"); + fd = hold_lock_file_for_update(&lock, pidfile_path, LOCK_DIE_ON_ERROR); if (!force) { static char locking_host[128]; int should_exit; - fp = fopen(git_path("gc.pid"), "r"); + fp = fopen(pidfile_path, "r"); memset(locking_host, 0, sizeof(locking_host)); should_exit = fp != NULL && @@@ -240,7 -243,7 +256,7 @@@ * running. */ time(NULL) - st.st_mtime <= 12 * 3600 && - fscanf(fp, "%"PRIuMAX" %127c", &pid, locking_host) == 2 && + fscanf(fp, "%"SCNuMAX" %127c", &pid, locking_host) == 2 && /* be gentle to concurrent "gc" on remote hosts */ (strcmp(locking_host, my_host) || !kill(pid, 0) || errno == EPERM); if (fp != NULL) @@@ -249,7 -252,6 +265,7 @@@ if (fd >= 0) rollback_lock_file(&lock); *ret_pid = pid; + free(pidfile_path); return locking_host; } } @@@ -259,29 -261,14 +275,29 @@@ write_in_full(fd, sb.buf, sb.len); strbuf_release(&sb); commit_lock_file(&lock); - - pidfile = git_pathdup("gc.pid"); - sigchain_push_common(remove_pidfile_on_signal); - atexit(remove_pidfile); - + register_tempfile(&pidfile, pidfile_path); + free(pidfile_path); return NULL; } +static int report_last_gc_error(void) +{ + struct strbuf sb = STRBUF_INIT; + int ret; + + ret = strbuf_read_file(&sb, git_path("gc.log"), 0); + if (ret > 0) + return error(_("The last gc run reported the following. " + "Please correct the root cause\n" + "and remove %s.\n" + "Automatic cleanup will not be performed " + "until the file is removed.\n\n" + "%s"), + git_path("gc.log"), sb.buf); + strbuf_release(&sb); + return 0; +} + static int gc_before_repack(void) { if (pack_refs && run_command_v_opt(pack_refs_cmd.argv, RUN_GIT_CMD)) @@@ -303,7 -290,6 +319,7 @@@ int cmd_gc(int argc, const char **argv int force = 0; const char *name; pid_t pid; + int daemonized = 0; struct option builtin_gc_options[] = { OPT__QUIET(&quiet, N_("suppress progress reporting")), @@@ -360,16 -346,13 +376,16 @@@ fprintf(stderr, _("See \"git help gc\" for manual housekeeping.\n")); } if (detach_auto) { + if (report_last_gc_error()) + return -1; + if (gc_before_repack()) return -1; /* * failure to daemonize is ok, we'll continue * in foreground */ - daemonize(); + daemonized = !daemonize(); } } else add_repack_all_option(); @@@ -382,29 -365,18 +398,29 @@@ name, (uintmax_t)pid); } + if (daemonized) { + hold_lock_file_for_update(&log_lock, + git_path("gc.log"), + LOCK_DIE_ON_ERROR); + dup2(get_lock_file_fd(&log_lock), 2); + sigchain_push_common(process_log_file_on_signal); + atexit(process_log_file_at_exit); + } + if (gc_before_repack()) return -1; - if (run_command_v_opt(repack.argv, RUN_GIT_CMD)) - return error(FAILED_RUN, repack.argv[0]); + if (!repository_format_precious_objects) { + if (run_command_v_opt(repack.argv, RUN_GIT_CMD)) + return error(FAILED_RUN, repack.argv[0]); - if (prune_expire) { - argv_array_push(&prune, prune_expire); - if (quiet) - argv_array_push(&prune, "--no-progress"); - if (run_command_v_opt(prune.argv, RUN_GIT_CMD)) - return error(FAILED_RUN, prune.argv[0]); + if (prune_expire) { + argv_array_push(&prune, prune_expire); + if (quiet) + argv_array_push(&prune, "--no-progress"); + if (run_command_v_opt(prune.argv, RUN_GIT_CMD)) + return error(FAILED_RUN, prune.argv[0]); + } } if (prune_worktrees_expire) { @@@ -416,6 -388,11 +432,11 @@@ if (run_command_v_opt(rerere.argv, RUN_GIT_CMD)) return error(FAILED_RUN, rerere.argv[0]); + report_garbage = report_pack_garbage; + reprepare_packed_git(); + if (pack_garbage.nr > 0) + clean_pack_garbage(); + if (auto_gc && too_many_loose_objects()) warning(_("There are too many unreachable loose objects; " "run 'git prune' to remove them.")); diff --combined cache.h index 3ba0b8f3d7,c6de1e9c0e..736abc03a4 --- a/cache.h +++ b/cache.h @@@ -397,7 -397,6 +397,7 @@@ static inline enum object_type object_t #define EXEC_PATH_ENVIRONMENT "GIT_EXEC_PATH" #define CEILING_DIRECTORIES_ENVIRONMENT "GIT_CEILING_DIRECTORIES" #define NO_REPLACE_OBJECTS_ENVIRONMENT "GIT_NO_REPLACE_OBJECTS" +#define GIT_REPLACE_REF_BASE_ENVIRONMENT "GIT_REPLACE_REF_BASE" #define GITATTRIBUTES_FILE ".gitattributes" #define INFOATTRIBUTES_FILE "info/attributes" #define ATTRIBUTE_MACRO_PREFIX "[attr]" @@@ -443,22 -442,11 +443,22 @@@ extern char *get_object_directory(void) extern char *get_index_file(void); extern char *get_graft_file(void); extern int set_git_dir(const char *path); +extern int get_common_dir_noenv(struct strbuf *sb, const char *gitdir); 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_git_work_tree(void); -extern const char *read_gitfile(const char *path); + +#define READ_GITFILE_ERR_STAT_FAILED 1 +#define READ_GITFILE_ERR_NOT_A_FILE 2 +#define READ_GITFILE_ERR_OPEN_FAILED 3 +#define READ_GITFILE_ERR_READ_FAILED 4 +#define READ_GITFILE_ERR_INVALID_FORMAT 5 +#define READ_GITFILE_ERR_NO_PATH 6 +#define READ_GITFILE_ERR_NOT_A_REPO 7 +#define READ_GITFILE_ERR_TOO_LARGE 8 +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 void set_git_work_tree(const char *tree); @@@ -521,8 -509,7 +521,8 @@@ extern int write_locked_index(struct in extern int discard_index(struct index_state *); extern int unmerged_index(const struct index_state *); extern int verify_path(const char *path); -extern struct cache_entry *index_dir_exists(struct index_state *istate, const char *name, int namelen); +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); extern int index_name_pos(const struct index_state *, const char *name, int namelen); #define ADD_CACHE_OK_TO_ADD 1 /* Ok to add */ @@@ -598,6 -585,8 +598,6 @@@ 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 delete_ref(const char *, const unsigned char *sha1, unsigned int flags); - /* Environment bits from configuration mechanism */ extern int trust_executable_bit; extern int trust_ctime; @@@ -633,7 -622,6 +633,7 @@@ extern unsigned long pack_size_limit_cf * been sought but there were none. */ extern int check_replace_refs; +extern char *git_replace_ref_base; extern int fsync_object_files; extern int core_preload_index; @@@ -698,15 -686,8 +698,15 @@@ extern char *notes_ref_name extern int grafts_replace_parents; +/* + * GIT_REPO_VERSION is the version we write by default. The + * _READ variant is the highest number we know how to + * handle. + */ #define GIT_REPO_VERSION 0 +#define GIT_REPO_VERSION_READ 1 extern int repository_format_version; +extern int repository_format_precious_objects; extern int check_repository_format(void); #define MTIME_CHANGED 0x0001 @@@ -717,61 -698,22 +717,61 @@@ #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 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 char *git_path_buf(struct strbuf *buf, const char *fmt, ...) + __attribute__((format (printf, 2, 3))); +extern void 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))); - -/* Return a statically allocated filename matching the sha1 signature */ -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_path_submodule(const char *path, const char *fmt, ...) +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 @@@ -794,24 -736,7 +794,24 @@@ extern char *sha1_pack_name(const unsig */ extern char *sha1_pack_index_name(const unsigned char *sha1); -extern const char *find_unique_abbrev(const unsigned char *sha1, int); +/* + * Return an abbreviated sha1 unique within this repository's object database. + * 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 `_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 + * written (excluding the NUL terminator). + * + * Note that while this version avoids the static buffer, it is not fully + * reentrant, as it calls into other non-reentrant git code. + */ +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]; static inline int hashcmp(const unsigned char *sha1, const unsigned char *sha2) @@@ -1010,7 -935,7 +1010,7 @@@ extern int do_check_packed_object_crc extern int check_sha1_signature(const unsigned char *sha1, void *buf, unsigned long size, const char *type); -extern int move_temp_to_file(const char *tmpfile, const char *filename); +extern int finalize_object_file(const char *tmpfile, const char *filename); extern int has_sha1_pack(const unsigned char *sha1); @@@ -1093,24 -1018,78 +1093,24 @@@ extern int for_each_abbrev(const char * extern int get_sha1_hex(const char *hex, unsigned char *sha1); extern int get_oid_hex(const char *hex, struct object_id *sha1); -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 read_ref_full(const char *refname, int resolve_flags, - unsigned char *sha1, int *flags); -extern int read_ref(const char *refname, unsigned char *sha1); - /* - * Resolve a reference, recursively following symbolic refererences. - * - * Store the referred-to object's name in sha1 and return the name of - * the non-symbolic reference that ultimately pointed at it. The - * return value, if not NULL, is a pointer into either a static buffer - * or the input ref. - * - * If the reference cannot be resolved to an object, the behavior - * depends on the RESOLVE_REF_READING flag: - * - * - If RESOLVE_REF_READING is set, return NULL. - * - * - If RESOLVE_REF_READING is not set, clear sha1 and return the name of - * the last reference name in the chain, which will either be a non-symbolic - * reference or an undefined reference. If this is a prelude to - * "writing" to the ref, the return value is the name of the ref - * that will actually be created or changed. - * - * If the RESOLVE_REF_NO_RECURSE flag is passed, only resolves one - * level of symbolic reference. The value stored in sha1 for a symbolic - * reference will always be null_sha1 in this case, and the return - * value is the reference that the symref refers to directly. - * - * If flags is non-NULL, set the value that it points to the - * combination of REF_ISPACKED (if the reference was found among the - * packed references), REF_ISSYMREF (if the initial reference was a - * symbolic reference), REF_BAD_NAME (if the reference name is ill - * formed --- see RESOLVE_REF_ALLOW_BAD_NAME below), and REF_ISBROKEN - * (if the ref is malformed or has a bad name). See refs.h for more detail - * on each flag. + * Convert a binary sha1 to its hex equivalent. The `_r` variant is reentrant, + * and writes the NUL-terminated output to the buffer `out`, which must be at + * least `GIT_SHA1_HEXSZ + 1` bytes, and returns a pointer to out for + * convenience. * - * If ref is not a properly-formatted, normalized reference, return - * NULL. If more than MAXDEPTH recursive symbolic lookups are needed, - * give up and return NULL. + * The non-`_r` variant returns a static buffer, but uses a ring of 4 + * buffers, making it safe to make multiple calls for a single statement, like: * - * RESOLVE_REF_ALLOW_BAD_NAME allows resolving refs even when their - * name is invalid according to git-check-ref-format(1). If the name - * is bad then the value stored in sha1 will be null_sha1 and the two - * flags REF_ISBROKEN and REF_BAD_NAME will be set. - * - * Even with RESOLVE_REF_ALLOW_BAD_NAME, names that escape the refs/ - * directory and do not consist of all caps and underscores cannot be - * resolved. The function returns NULL for such ref names. - * Caps and underscores refers to the special refs, such as HEAD, - * FETCH_HEAD and friends, that all live outside of the refs/ directory. + * printf("%s -> %s", sha1_to_hex(one), sha1_to_hex(two)); */ -#define RESOLVE_REF_READING 0x01 -#define RESOLVE_REF_NO_RECURSE 0x02 -#define RESOLVE_REF_ALLOW_BAD_NAME 0x04 -extern const char *resolve_ref_unsafe(const char *ref, int resolve_flags, unsigned char *sha1, int *flags); -extern char *resolve_refdup(const char *ref, int resolve_flags, unsigned char *sha1, int *flags); - -extern int dwim_ref(const char *str, int len, unsigned char *sha1, char **ref); -extern int dwim_log(const char *str, int len, unsigned char *sha1, char **ref); +extern char *sha1_to_hex_r(char *out, const unsigned char *sha1); +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 *); extern int get_sha1_mb(const char *str, unsigned char *sha1); -/* - * Return true iff abbrev_name is a possible abbreviation for - * full_name according to the rules defined by ref_rev_parse_rules in - * refs.c. - */ -extern int refname_match(const char *abbrev_name, const char *full_name); - -extern int create_symref(const char *ref, const char *refs_heads_master, const char *logmsg); extern int validate_headref(const char *ref); extern int base_name_compare(const char *name1, int len1, int mode1, const char *name2, int len2, int mode2); @@@ -1126,30 -1105,18 +1126,30 @@@ extern void *read_object_with_reference extern struct object *peel_to_type(const char *name, int namelen, struct object *o, enum object_type); -enum date_mode { - DATE_NORMAL = 0, - DATE_RELATIVE, - DATE_SHORT, - DATE_LOCAL, - DATE_ISO8601, - DATE_ISO8601_STRICT, - DATE_RFC2822, - DATE_RAW +struct date_mode { + enum date_mode_type { + DATE_NORMAL = 0, + DATE_RELATIVE, + DATE_SHORT, + DATE_ISO8601, + DATE_ISO8601_STRICT, + DATE_RFC2822, + DATE_STRFTIME, + DATE_RAW + } type; + const char *strftime_fmt; + int local; }; -const char *show_date(unsigned long time, int timezone, enum date_mode mode); +/* + * Convenience helper for passing a constant type, like: + * + * show_date(t, tz, DATE_MODE(NORMAL)); + */ +#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, struct strbuf *timebuf); int parse_date(const char *date, struct strbuf *out); @@@ -1159,7 -1126,7 +1159,7 @@@ 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); -enum date_mode parse_date_format(const char *format); +void parse_date_format(const char *format, struct date_mode *mode); int date_overflows(unsigned long date); #define IDENT_STRICT 1 @@@ -1196,8 -1163,7 +1196,8 @@@ extern int split_ident_line(struct iden * the ident_split. It will also sanity-check the values and produce * a well-known sentinel date if they appear bogus. */ -const char *show_ident_date(const struct ident_split *id, enum date_mode mode); +const char *show_ident_date(const struct ident_split *id, + const struct date_mode *mode); /* * Compare split idents for equality or strict ordering. Note that we @@@ -1289,8 -1255,11 +1289,11 @@@ struct pack_entry extern struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path); - /* A hook for count-objects to report invalid files in pack directory */ - extern void (*report_garbage)(const char *desc, const char *path); + /* A hook to report invalid files in pack directory */ + #define PACKDIR_FILE_PACK 1 + #define PACKDIR_FILE_IDX 2 + #define PACKDIR_FILE_GARBAGE 4 + extern void (*report_garbage)(unsigned seen_bits, const char *path); extern void prepare_packed_git(void); extern void reprepare_packed_git(void); @@@ -1315,11 -1284,10 +1318,11 @@@ extern void close_pack_index(struct pac extern unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned long *); extern void close_pack_windows(struct packed_git *); +extern void close_all_packs(void); extern void unuse_pack(struct pack_window **); extern void free_pack_by_name(const char *); extern void clear_delta_base_cache(void); -extern struct packed_git *add_packed_git(const char *, int, int); +extern struct packed_git *add_packed_git(const char *path, size_t path_len, int local); /* * Return the SHA-1 of the nth object within the specified packfile. @@@ -1470,7 -1438,6 +1473,7 @@@ extern int git_config_with_options(conf int respect_includes); extern int git_config_early(config_fn_t fn, void *, const char *repo_config); 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 *); @@@ -1482,7 -1449,6 +1485,7 @@@ extern int git_config_pathname(const ch extern int git_config_set_in_file(const char *, const char *, const char *); extern int 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(const char *, const char *, const char *, int); extern int 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 *); @@@ -1619,9 -1585,8 +1622,9 @@@ static inline ssize_t write_str_in_full { return write_in_full(fd, str, strlen(str)); } -__attribute__((format (printf, 3, 4))) -extern int write_file(const char *path, int fatal, const char *fmt, ...); + +extern int write_file(const char *path, const char *fmt, ...); +extern int write_file_gently(const char *path, const char *fmt, ...); /* pager.c */ extern void setup_pager(void); diff --combined path.c index c740c4ff94,75ec2363fd..f28ace2963 --- a/path.c +++ b/path.c @@@ -91,279 -91,59 +91,279 @@@ static void replace_dir(struct strbuf * buf->buf[newlen] = '/'; } -static const char *common_list[] = { - "/branches", "/hooks", "/info", "!/logs", "/lost-found", - "/objects", "/refs", "/remotes", "/worktrees", "/rr-cache", "/svn", - "config", "!gc.pid", "packed-refs", "shallow", - NULL +struct common_dir { + /* Not considered garbage for report_linked_checkout_garbage */ + unsigned ignore_garbage:1; + unsigned is_dir:1; + /* Not common even though its parent is */ + unsigned exclude:1; + const char *dirname; }; -static void update_common_dir(struct strbuf *buf, int git_dir_len) +static struct common_dir common_list[] = { + { 0, 1, 0, "branches" }, + { 0, 1, 0, "hooks" }, + { 0, 1, 0, "info" }, + { 0, 0, 1, "info/sparse-checkout" }, + { 1, 1, 0, "logs" }, + { 1, 1, 1, "logs/HEAD" }, + { 0, 1, 1, "logs/refs/bisect" }, + { 0, 1, 0, "lost-found" }, + { 0, 1, 0, "objects" }, + { 0, 1, 0, "refs" }, + { 0, 1, 1, "refs/bisect" }, + { 0, 1, 0, "remotes" }, + { 0, 1, 0, "worktrees" }, + { 0, 1, 0, "rr-cache" }, + { 0, 1, 0, "svn" }, + { 0, 0, 0, "config" }, + { 1, 0, 0, "gc.pid" }, + { 0, 0, 0, "packed-refs" }, + { 0, 0, 0, "shallow" }, + { 0, 0, 0, NULL } +}; + +/* + * A compressed trie. A trie node consists of zero or more characters that + * are common to all elements with this prefix, optionally followed by some + * children. If value is not NULL, the trie node is a terminal node. + * + * For example, consider the following set of strings: + * abc + * def + * definite + * definition + * + * The trie would look look like: + * root: len = 0, children a and d non-NULL, value = NULL. + * a: len = 2, contents = bc, value = (data for "abc") + * d: len = 2, contents = ef, children i non-NULL, value = (data for "def") + * i: len = 3, contents = nit, children e and i non-NULL, value = NULL + * e: len = 0, children all NULL, value = (data for "definite") + * i: len = 2, contents = on, children all NULL, + * value = (data for "definition") + */ +struct trie { + struct trie *children[256]; + int len; + char *contents; + void *value; +}; + +static struct trie *make_trie_node(const char *key, void *value) { - char *base = buf->buf + git_dir_len; - const char **p; - - if (is_dir_file(base, "logs", "HEAD") || - is_dir_file(base, "info", "sparse-checkout")) - return; /* keep this in $GIT_DIR */ - for (p = common_list; *p; p++) { - const char *path = *p; - int is_dir = 0; - if (*path == '!') - path++; - if (*path == '/') { - path++; - is_dir = 1; + struct trie *new_node = xcalloc(1, sizeof(*new_node)); + new_node->len = strlen(key); + if (new_node->len) { + new_node->contents = xmalloc(new_node->len); + memcpy(new_node->contents, key, new_node->len); + } + new_node->value = value; + return new_node; +} + +/* + * Add a key/value pair to a trie. The key is assumed to be \0-terminated. + * If there was an existing value for this key, return it. + */ +static void *add_to_trie(struct trie *root, const char *key, void *value) +{ + struct trie *child; + void *old; + int i; + + if (!*key) { + /* we have reached the end of the key */ + old = root->value; + root->value = value; + return old; + } + + for (i = 0; i < root->len; i++) { + if (root->contents[i] == key[i]) + continue; + + /* + * Split this node: child will contain this node's + * existing children. + */ + child = malloc(sizeof(*child)); + memcpy(child->children, root->children, sizeof(root->children)); + + child->len = root->len - i - 1; + if (child->len) { + child->contents = xstrndup(root->contents + i + 1, + child->len); } - if (is_dir && dir_prefix(base, path)) { - replace_dir(buf, git_dir_len, get_git_common_dir()); - return; + child->value = root->value; + root->value = NULL; + root->len = i; + + memset(root->children, 0, sizeof(root->children)); + root->children[(unsigned char)root->contents[i]] = child; + + /* This is the newly-added child. */ + root->children[(unsigned char)key[i]] = + make_trie_node(key + i + 1, value); + return NULL; + } + + /* We have matched the entire compressed section */ + if (key[i]) { + child = root->children[(unsigned char)key[root->len]]; + if (child) { + return add_to_trie(child, key + root->len + 1, value); + } else { + child = make_trie_node(key + root->len + 1, value); + root->children[(unsigned char)key[root->len]] = child; + return NULL; } - if (!is_dir && !strcmp(base, path)) { - replace_dir(buf, git_dir_len, get_git_common_dir()); - return; + } + + old = root->value; + root->value = value; + return old; +} + +typedef int (*match_fn)(const char *unmatched, void *data, void *baton); + +/* + * Search a trie for some key. Find the longest /-or-\0-terminated + * prefix of the key for which the trie contains a value. Call fn + * with the unmatched portion of the key and the found value, and + * return its return value. If there is no such prefix, return -1. + * + * The key is partially normalized: consecutive slashes are skipped. + * + * For example, consider the trie containing only [refs, + * refs/worktree] (both with values). + * + * | key | unmatched | val from node | return value | + * |-----------------|------------|---------------|--------------| + * | a | not called | n/a | -1 | + * | refs | \0 | refs | as per fn | + * | refs/ | / | refs | as per fn | + * | refs/w | /w | refs | as per fn | + * | refs/worktree | \0 | refs/worktree | as per fn | + * | refs/worktree/ | / | refs/worktree | as per fn | + * | refs/worktree/a | /a | refs/worktree | as per fn | + * |-----------------|------------|---------------|--------------| + * + */ +static int trie_find(struct trie *root, const char *key, match_fn fn, + void *baton) +{ + int i; + int result; + struct trie *child; + + if (!*key) { + /* we have reached the end of the key */ + if (root->value && !root->len) + return fn(key, root->value, baton); + else + return -1; + } + + for (i = 0; i < root->len; i++) { + /* Partial path normalization: skip consecutive slashes. */ + if (key[i] == '/' && key[i+1] == '/') { + key++; + continue; } + if (root->contents[i] != key[i]) + return -1; } + + /* Matched the entire compressed section */ + key += i; + if (!*key) + /* End of key */ + return fn(key, root->value, baton); + + /* Partial path normalization: skip consecutive slashes */ + while (key[0] == '/' && key[1] == '/') + key++; + + child = root->children[(unsigned char)*key]; + if (child) + result = trie_find(child, key + 1, fn, baton); + else + result = -1; + + if (result >= 0 || (*key != '/' && *key != 0)) + return result; + if (root->value) + return fn(key, root->value, baton); + else + return -1; +} + +static struct trie common_trie; +static int common_trie_done_setup; + +static void init_common_trie(void) +{ + struct common_dir *p; + + if (common_trie_done_setup) + return; + + for (p = common_list; p->dirname; p++) + add_to_trie(&common_trie, p->dirname, p); + + common_trie_done_setup = 1; +} + +/* + * Helper function for update_common_dir: returns 1 if the dir + * prefix is common. + */ +static int check_common(const char *unmatched, void *value, void *baton) +{ + struct common_dir *dir = value; + + if (!dir) + return 0; + + if (dir->is_dir && (unmatched[0] == 0 || unmatched[0] == '/')) + return !dir->exclude; + + if (!dir->is_dir && unmatched[0] == 0) + return !dir->exclude; + + return 0; +} + +static void update_common_dir(struct strbuf *buf, int git_dir_len, + const char *common_dir) +{ + char *base = buf->buf + git_dir_len; + init_common_trie(); + if (!common_dir) + common_dir = get_git_common_dir(); + if (trie_find(&common_trie, base, check_common, NULL) > 0) + replace_dir(buf, git_dir_len, common_dir); } void report_linked_checkout_garbage(void) { struct strbuf sb = STRBUF_INIT; - const char **p; + const struct common_dir *p; int len; if (!git_common_dir_env) return; strbuf_addf(&sb, "%s/", get_git_dir()); len = sb.len; - for (p = common_list; *p; p++) { - const char *path = *p; - if (*path == '!') + for (p = common_list; p->dirname; p++) { + const char *path = p->dirname; + if (p->ignore_garbage) continue; strbuf_setlen(&sb, len); strbuf_addstr(&sb, path); if (file_exists(sb.buf)) - report_garbage("unused in linked checkout", sb.buf); + report_garbage(PACKDIR_FILE_GARBAGE, sb.buf); } strbuf_release(&sb); } @@@ -380,7 -160,7 +380,7 @@@ static void adjust_git_path(struct strb else if (git_db_env && dir_prefix(base, "objects")) replace_dir(buf, git_dir_len + 7, get_object_directory()); else if (git_common_dir_env) - update_common_dir(buf, git_dir_len); + update_common_dir(buf, git_dir_len, NULL); } static void do_git_path(struct strbuf *buf, const char *fmt, va_list args) @@@ -395,16 -175,6 +395,16 @@@ strbuf_cleanup_path(buf); } +char *git_path_buf(struct strbuf *buf, const char *fmt, ...) +{ + va_list args; + strbuf_reset(buf); + va_start(args, fmt); + do_git_path(buf, fmt, args); + va_end(args); + return buf->buf; +} + void strbuf_git_path(struct strbuf *sb, const char *fmt, ...) { va_list args; @@@ -454,15 -224,15 +454,15 @@@ const char *mkpath(const char *fmt, ... return cleanup_path(pathname->buf); } -const char *git_path_submodule(const char *path, const char *fmt, ...) +static void do_submodule_path(struct strbuf *buf, const char *path, + const char *fmt, va_list args) { - struct strbuf *buf = get_pathname(); const char *git_dir; - va_list args; + struct strbuf git_submodule_common_dir = STRBUF_INIT; + struct strbuf git_submodule_dir = STRBUF_INIT; strbuf_addstr(buf, path); - if (buf->len && buf->buf[buf->len - 1] != '/') - strbuf_addch(buf, '/'); + strbuf_complete(buf, '/'); strbuf_addstr(buf, ".git"); git_dir = read_gitfile(buf->buf); @@@ -471,36 -241,12 +471,36 @@@ strbuf_addstr(buf, git_dir); } strbuf_addch(buf, '/'); + strbuf_addstr(&git_submodule_dir, buf->buf); - va_start(args, fmt); strbuf_vaddf(buf, fmt, args); - va_end(args); + + if (get_common_dir_noenv(&git_submodule_common_dir, git_submodule_dir.buf)) + update_common_dir(buf, git_submodule_dir.len, git_submodule_common_dir.buf); + strbuf_cleanup_path(buf); - return buf->buf; + + strbuf_release(&git_submodule_dir); + strbuf_release(&git_submodule_common_dir); +} + +char *git_pathdup_submodule(const char *path, const char *fmt, ...) +{ + va_list args; + struct strbuf buf = STRBUF_INIT; + va_start(args, fmt); + do_submodule_path(&buf, path, fmt, args); + va_end(args); + return strbuf_detach(&buf, NULL); +} + +void strbuf_git_path_submodule(struct strbuf *buf, const char *path, + const char *fmt, ...) +{ + va_list args; + va_start(args, fmt); + do_submodule_path(buf, path, fmt, args); + va_end(args); } int validate_headref(const char *path) @@@ -620,8 -366,8 +620,8 @@@ return_null */ const char *enter_repo(const char *path, int strict) { - static char used_path[PATH_MAX]; - static char validated_path[PATH_MAX]; + static struct strbuf validated_path = STRBUF_INIT; + static struct strbuf used_path = STRBUF_INIT; if (!path) return NULL; @@@ -636,57 -382,52 +636,57 @@@ while ((1 < len) && (path[len-1] == '/')) len--; + /* + * We can handle arbitrary-sized buffers, but this remains as a + * sanity check on untrusted input. + */ if (PATH_MAX <= len) return NULL; - strncpy(used_path, path, len); used_path[len] = 0 ; - strcpy(validated_path, used_path); - if (used_path[0] == '~') { - char *newpath = expand_user_path(used_path); - if (!newpath || (PATH_MAX - 10 < strlen(newpath))) { - free(newpath); + strbuf_reset(&used_path); + strbuf_reset(&validated_path); + strbuf_add(&used_path, path, len); + strbuf_add(&validated_path, path, len); + + if (used_path.buf[0] == '~') { + char *newpath = expand_user_path(used_path.buf); + if (!newpath) return NULL; - } - /* - * Copy back into the static buffer. A pity - * since newpath was not bounded, but other - * branches of the if are limited by PATH_MAX - * anyway. - */ - strcpy(used_path, newpath); free(newpath); + strbuf_attach(&used_path, newpath, strlen(newpath), + strlen(newpath)); } - else if (PATH_MAX - 10 < len) - return NULL; - len = strlen(used_path); for (i = 0; suffix[i]; i++) { struct stat st; - strcpy(used_path + len, suffix[i]); - if (!stat(used_path, &st) && + size_t baselen = used_path.len; + strbuf_addstr(&used_path, suffix[i]); + if (!stat(used_path.buf, &st) && (S_ISREG(st.st_mode) || - (S_ISDIR(st.st_mode) && is_git_directory(used_path)))) { - strcat(validated_path, suffix[i]); + (S_ISDIR(st.st_mode) && is_git_directory(used_path.buf)))) { + strbuf_addstr(&validated_path, suffix[i]); break; } + strbuf_setlen(&used_path, baselen); } if (!suffix[i]) return NULL; - gitfile = read_gitfile(used_path) ; + gitfile = read_gitfile(used_path.buf); + if (gitfile) { + strbuf_reset(&used_path); + strbuf_addstr(&used_path, gitfile); + } + if (chdir(used_path.buf)) + return NULL; + path = validated_path.buf; + } + else { + const char *gitfile = read_gitfile(path); if (gitfile) - strcpy(used_path, gitfile); - if (chdir(used_path)) + path = gitfile; + if (chdir(path)) return NULL; - path = validated_path; } - else if (chdir(path)) - return NULL; - if (access("objects", X_OK) == 0 && access("refs", X_OK) == 0 && - validate_headref("HEAD") == 0) { + if (is_git_directory(".")) { set_git_dir("."); check_repository_format(); return path; @@@ -865,7 -606,7 +865,7 @@@ const char *relative_path(const char *i */ const char *remove_leading_path(const char *in, const char *prefix) { - static char buf[PATH_MAX + 1]; + static struct strbuf buf = STRBUF_INIT; int i = 0, j = 0; if (!prefix || !prefix[0]) @@@ -894,13 -635,11 +894,13 @@@ return in; while (is_dir_sep(in[j])) j++; + + strbuf_reset(&buf); if (!in[j]) - strcpy(buf, "."); + strbuf_addstr(&buf, "."); else - strcpy(buf, in + j); - return buf; + strbuf_addstr(&buf, in + j); + return buf.buf; } /* @@@ -922,11 -661,6 +922,11 @@@ * normalized, any time "../" eats up to the prefix_len part, * prefix_len is reduced. In the end prefix_len is the remaining * prefix that has not been overridden by user pathspec. + * + * NEEDSWORK: This function doesn't perform normalization w.r.t. trailing '/'. + * For everything but the root folder itself, the normalized path should not + * end with a '/', then the callers need to be fixed up accordingly. + * */ int normalize_path_copy_len(char *dst, const char *src, int *prefix_len) { @@@ -1184,13 -918,3 +1184,13 @@@ char *xdg_config_home(const char *filen return mkpathdup("%s/.config/git/%s", home, filename); return NULL; } + +GIT_PATH_FUNC(git_path_cherry_pick_head, "CHERRY_PICK_HEAD") +GIT_PATH_FUNC(git_path_revert_head, "REVERT_HEAD") +GIT_PATH_FUNC(git_path_squash_msg, "SQUASH_MSG") +GIT_PATH_FUNC(git_path_merge_msg, "MERGE_MSG") +GIT_PATH_FUNC(git_path_merge_rr, "MERGE_RR") +GIT_PATH_FUNC(git_path_merge_mode, "MERGE_MODE") +GIT_PATH_FUNC(git_path_merge_head, "MERGE_HEAD") +GIT_PATH_FUNC(git_path_fetch_head, "FETCH_HEAD") +GIT_PATH_FUNC(git_path_shallow, "shallow") diff --combined sha1_file.c index c5b31de9aa,0c0b652949..3d56746a9b --- a/sha1_file.c +++ b/sha1_file.c @@@ -208,25 -208,44 +208,25 @@@ const char *sha1_file_name(const unsign * provided by the caller. which should be "pack" or "idx". */ static char *sha1_get_pack_name(const unsigned char *sha1, - char **name, char **base, const char *which) + struct strbuf *buf, + const char *which) { - static const char hex[] = "0123456789abcdef"; - char *buf; - int i; - - if (!*base) { - const char *sha1_file_directory = get_object_directory(); - int len = strlen(sha1_file_directory); - *base = xmalloc(len + 60); - sprintf(*base, "%s/pack/pack-1234567890123456789012345678901234567890.%s", - sha1_file_directory, which); - *name = *base + len + 11; - } - - buf = *name; - - for (i = 0; i < 20; i++) { - unsigned int val = *sha1++; - *buf++ = hex[val >> 4]; - *buf++ = hex[val & 0xf]; - } - - return *base; + strbuf_reset(buf); + strbuf_addf(buf, "%s/pack/pack-%s.%s", get_object_directory(), + sha1_to_hex(sha1), which); + return buf->buf; } char *sha1_pack_name(const unsigned char *sha1) { - static char *name, *base; - - return sha1_get_pack_name(sha1, &name, &base, "pack"); + static struct strbuf buf = STRBUF_INIT; + return sha1_get_pack_name(sha1, &buf, "pack"); } char *sha1_pack_index_name(const unsigned char *sha1) { - static char *name, *base; - - return sha1_get_pack_name(sha1, &name, &base, "idx"); + static struct strbuf buf = STRBUF_INIT; + return sha1_get_pack_name(sha1, &buf, "idx"); } struct alternate_object_database *alt_odb_list; @@@ -358,12 -377,15 +358,12 @@@ void read_info_alternates(const char * char *map; size_t mapsz; struct stat st; - const char alt_file_name[] = "info/alternates"; - /* Given that relative_base is no longer than PATH_MAX, - ensure that "path" has enough space to append "/", the - file name, "info/alternates", and a trailing NUL. */ - char path[PATH_MAX + 1 + sizeof alt_file_name]; + char *path; int fd; - sprintf(path, "%s/%s", relative_base, alt_file_name); + path = xstrfmt("%s/info/alternates", relative_base); fd = git_open_noatime(path); + free(path); if (fd < 0) return; if (fstat(fd, &st) || (st.st_size == 0)) { @@@ -382,46 -404,13 +382,46 @@@ void add_to_alternates_file(const char *reference) { struct lock_file *lock = xcalloc(1, sizeof(struct lock_file)); - int fd = hold_lock_file_for_append(lock, git_path("objects/info/alternates"), LOCK_DIE_ON_ERROR); - const char *alt = mkpath("%s\n", reference); - write_or_die(fd, alt, strlen(alt)); - if (commit_lock_file(lock)) - die("could not close alternates file"); - if (alt_odb_tail) - link_alt_odb_entries(alt, strlen(alt), '\n', NULL, 0); + char *alts = git_pathdup("objects/info/alternates"); + FILE *in, *out; + + hold_lock_file_for_update(lock, alts, LOCK_DIE_ON_ERROR); + out = fdopen_lock_file(lock, "w"); + if (!out) + die_errno("unable to fdopen alternates lockfile"); + + in = fopen(alts, "r"); + if (in) { + struct strbuf line = STRBUF_INIT; + int found = 0; + + while (strbuf_getline(&line, in, '\n') != EOF) { + if (!strcmp(reference, line.buf)) { + found = 1; + break; + } + fprintf_or_die(out, "%s\n", line.buf); + } + + strbuf_release(&line); + fclose(in); + + if (found) { + rollback_lock_file(lock); + lock = NULL; + } + } + else if (errno != ENOENT) + die_errno("unable to read alternates file"); + + if (lock) { + fprintf_or_die(out, "%s\n", reference); + if (commit_lock_file(lock)) + die_errno("unable to move new alternates file into place"); + if (alt_odb_tail) + link_alt_odb_entries(reference, strlen(reference), '\n', NULL, 0); + } + free(alts); } int foreach_alt_odb(alt_odb_fn fn, void *cb) @@@ -652,15 -641,13 +652,15 @@@ static int check_packed_git_idx(const c int open_pack_index(struct packed_git *p) { char *idx_name; + size_t len; int ret; if (p->index_data) return 0; - idx_name = xstrdup(p->pack_name); - strcpy(idx_name + strlen(idx_name) - strlen(".pack"), ".idx"); + if (!strip_suffix(p->pack_name, ".pack", &len)) + die("BUG: pack_name does not end in .pack"); + idx_name = xstrfmt("%.*s.idx", (int)len, p->pack_name); ret = check_packed_git_idx(idx_name, p); free(idx_name); return ret; @@@ -769,37 -756,6 +769,37 @@@ void close_pack_windows(struct packed_g } } +static int close_pack_fd(struct packed_git *p) +{ + if (p->pack_fd < 0) + return 0; + + close(p->pack_fd); + pack_open_fds--; + p->pack_fd = -1; + + return 1; +} + +static void close_pack(struct packed_git *p) +{ + close_pack_windows(p); + close_pack_fd(p); + close_pack_index(p); +} + +void close_all_packs(void) +{ + struct packed_git *p; + + for (p = packed_git; p; p = p->next) + if (p->do_not_close) + die("BUG! Want to close pack marked 'do-not-close'"); + else + close_pack(p); +} + + /* * The LRU pack is the one with the oldest MRU window, preferring packs * with no used windows, or the oldest mtime if it has no windows allocated. @@@ -867,8 -823,12 +867,8 @@@ static int close_one_pack(void find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse); } - if (lru_p) { - close(lru_p->pack_fd); - pack_open_fds--; - lru_p->pack_fd = -1; - return 1; - } + if (lru_p) + return close_pack_fd(lru_p); return 0; } @@@ -908,7 -868,12 +908,7 @@@ void free_pack_by_name(const char *pack p = *pp; if (strcmp(pack_name, p->pack_name) == 0) { clear_delta_base_cache(); - close_pack_windows(p); - if (p->pack_fd != -1) { - close(p->pack_fd); - pack_open_fds--; - } - close_pack_index(p); + close_pack(p); free(p->bad_object_sha1); *pp = p->next; if (last_found_pack == p) @@@ -1042,7 -1007,11 +1042,7 @@@ static int open_packed_git(struct packe { if (!open_packed_git_1(p)) return 0; - if (p->pack_fd != -1) { - close(p->pack_fd); - pack_open_fds--; - p->pack_fd = -1; - } + close_pack_fd(p); return -1; } @@@ -1108,8 -1077,11 +1108,8 @@@ unsigned char *use_pack(struct packed_g p->pack_name, strerror(errno)); if (!win->offset && win->len == p->pack_size - && !p->do_not_close) { - close(p->pack_fd); - pack_open_fds--; - p->pack_fd = -1; - } + && !p->do_not_close) + close_pack_fd(p); pack_mmap_calls++; pack_open_windows++; if (pack_mapped > peak_pack_mapped) @@@ -1144,12 -1116,11 +1144,12 @@@ static void try_to_free_pack_memory(siz release_pack_memory(size); } -struct packed_git *add_packed_git(const char *path, int path_len, int local) +struct packed_git *add_packed_git(const char *path, size_t path_len, int local) { static int have_set_try_to_free_routine; struct stat st; - struct packed_git *p = alloc_packed_git(path_len + 2); + size_t alloc; + struct packed_git *p; if (!have_set_try_to_free_routine) { have_set_try_to_free_routine = 1; @@@ -1160,22 -1131,18 +1160,22 @@@ * Make sure a corresponding .pack file exists and that * the index looks sane. */ - path_len -= strlen(".idx"); - if (path_len < 1) { - free(p); + if (!strip_suffix_mem(path, &path_len, ".idx")) return NULL; - } + + /* + * ".pack" is long enough to hold any suffix we're adding (and + * the use xsnprintf double-checks that) + */ + alloc = path_len + strlen(".pack") + 1; + p = alloc_packed_git(alloc); memcpy(p->pack_name, path, path_len); - strcpy(p->pack_name + path_len, ".keep"); + xsnprintf(p->pack_name + path_len, alloc - path_len, ".keep"); if (!access(p->pack_name, F_OK)) p->pack_keep = 1; - strcpy(p->pack_name + path_len, ".pack"); + xsnprintf(p->pack_name + path_len, alloc - path_len, ".pack"); if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) { free(p); return NULL; @@@ -1195,10 -1162,9 +1195,10 @@@ struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path) { const char *path = sha1_pack_name(sha1); - struct packed_git *p = alloc_packed_git(strlen(path) + 1); + int alloc = strlen(path) + 1; + struct packed_git *p = alloc_packed_git(alloc); - strcpy(p->pack_name, path); + memcpy(p->pack_name, path, alloc); /* includes NUL */ hashcpy(p->sha1, sha1); if (check_packed_git_idx(idx_path, p)) { free(p); @@@ -1217,27 -1183,16 +1217,16 @@@ void install_packed_git(struct packed_g packed_git = pack; } - void (*report_garbage)(const char *desc, const char *path); + void (*report_garbage)(unsigned seen_bits, const char *path); static void report_helper(const struct string_list *list, int seen_bits, int first, int last) { - const char *msg; - switch (seen_bits) { - case 0: - msg = "no corresponding .idx or .pack"; - break; - case 1: - msg = "no corresponding .idx"; - break; - case 2: - msg = "no corresponding .pack"; - break; - default: + if (seen_bits == (PACKDIR_FILE_PACK|PACKDIR_FILE_IDX)) return; - } + for (; first < last; first++) - report_garbage(msg, list->items[first].string); + report_garbage(seen_bits, list->items[first].string); } static void report_pack_garbage(struct string_list *list) @@@ -1260,7 -1215,7 +1249,7 @@@ if (baselen == -1) { const char *dot = strrchr(path, '.'); if (!dot) { - report_garbage("garbage found", path); + report_garbage(PACKDIR_FILE_GARBAGE, path); continue; } baselen = dot - path + 1; @@@ -1332,7 -1287,7 +1321,7 @@@ static void prepare_packed_git_one(cha ends_with(de->d_name, ".keep")) string_list_append(&garbage, path.buf); else - report_garbage("garbage found", path.buf); + report_garbage(PACKDIR_FILE_GARBAGE, path.buf); } closedir(dir); report_pack_garbage(&garbage); @@@ -1468,7 -1423,7 +1457,7 @@@ int check_sha1_signature(const unsigne return -1; /* Generate the header */ - hdrlen = sprintf(hdr, "%s %lu", typename(obj_type), size) + 1; + hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(obj_type), size) + 1; /* Sha1.. */ git_SHA1_Init(&c); @@@ -1495,10 -1450,7 +1484,10 @@@ int git_open_noatime(const char *name static int sha1_file_open_flag = O_NOATIME; for (;;) { - int fd = open(name, O_RDONLY | sha1_file_open_flag); + int fd; + + errno = 0; + fd = open(name, O_RDONLY | sha1_file_open_flag); if (fd >= 0) return fd; @@@ -2126,7 -2078,7 +2115,7 @@@ static unsigned long pack_entry_hash(st { unsigned long hash; - hash = (unsigned long)p + (unsigned long)base_offset; + hash = (unsigned long)(intptr_t)p + (unsigned long)base_offset; hash += (hash >> 8) + (hash >> 16); return hash % MAX_DELTA_CACHE; } @@@ -2934,7 -2886,7 +2923,7 @@@ static void write_sha1_file_prepare(con git_SHA_CTX c; /* Generate the header */ - *hdrlen = sprintf(hdr, "%s %lu", type, len)+1; + *hdrlen = xsnprintf(hdr, *hdrlen, "%s %lu", type, len)+1; /* Sha1.. */ git_SHA1_Init(&c); @@@ -2945,8 -2897,11 +2934,8 @@@ /* * Move the just written object into its final resting place. - * NEEDSWORK: this should be renamed to finalize_temp_file() as - * "moving" is only a part of what it does, when no patch between - * master to pu changes the call sites of this function. */ -int move_temp_to_file(const char *tmpfile, const char *filename) +int finalize_object_file(const char *tmpfile, const char *filename) { int ret = 0; @@@ -2997,7 -2952,7 +2986,7 @@@ int hash_sha1_file(const void *buf, uns unsigned char *sha1) { char hdr[32]; - int hdrlen; + int hdrlen = sizeof(hdr); write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen); return 0; } @@@ -3027,31 -2982,29 +3016,31 @@@ static inline int directory_size(const * We want to avoid cross-directory filename renames, because those * can have problems on various filesystems (FAT, NFS, Coda). */ -static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename) +static int create_tmpfile(struct strbuf *tmp, const char *filename) { int fd, dirlen = directory_size(filename); - if (dirlen + 20 > bufsiz) { - errno = ENAMETOOLONG; - return -1; - } - memcpy(buffer, filename, dirlen); - strcpy(buffer + dirlen, "tmp_obj_XXXXXX"); - fd = git_mkstemp_mode(buffer, 0444); + strbuf_reset(tmp); + strbuf_add(tmp, filename, dirlen); + strbuf_addstr(tmp, "tmp_obj_XXXXXX"); + fd = git_mkstemp_mode(tmp->buf, 0444); if (fd < 0 && dirlen && errno == ENOENT) { - /* Make sure the directory exists */ - memcpy(buffer, filename, dirlen); - buffer[dirlen-1] = 0; - if (mkdir(buffer, 0777) && errno != EEXIST) + /* + * Make sure the directory exists; note that the contents + * of the buffer are undefined after mkstemp returns an + * error, so we have to rewrite the whole buffer from + * scratch. + */ + strbuf_reset(tmp); + strbuf_add(tmp, filename, dirlen - 1); + if (mkdir(tmp->buf, 0777) && errno != EEXIST) return -1; - if (adjust_shared_perm(buffer)) + if (adjust_shared_perm(tmp->buf)) return -1; /* Try again */ - strcpy(buffer + dirlen - 1, "/tmp_obj_XXXXXX"); - fd = git_mkstemp_mode(buffer, 0444); + strbuf_addstr(tmp, "/tmp_obj_XXXXXX"); + fd = git_mkstemp_mode(tmp->buf, 0444); } return fd; } @@@ -3064,10 -3017,10 +3053,10 @@@ static int write_loose_object(const uns git_zstream stream; git_SHA_CTX c; unsigned char parano_sha1[20]; - static char tmp_file[PATH_MAX]; + static struct strbuf tmp_file = STRBUF_INIT; const char *filename = sha1_file_name(sha1); - fd = create_tmpfile(tmp_file, sizeof(tmp_file), filename); + fd = create_tmpfile(&tmp_file, filename); if (fd < 0) { if (errno == EACCES) return error("insufficient permission for adding an object to repository database %s", get_object_directory()); @@@ -3116,12 -3069,12 +3105,12 @@@ struct utimbuf utb; utb.actime = mtime; utb.modtime = mtime; - if (utime(tmp_file, &utb) < 0) + if (utime(tmp_file.buf, &utb) < 0) warning("failed utime() on %s: %s", - tmp_file, strerror(errno)); + tmp_file.buf, strerror(errno)); } - return move_temp_to_file(tmp_file, filename); + return finalize_object_file(tmp_file.buf, filename); } static int freshen_loose_object(const unsigned char *sha1) @@@ -3145,7 -3098,7 +3134,7 @@@ static int freshen_packed_object(const int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *sha1) { char hdr[32]; - int hdrlen; + int hdrlen = sizeof(hdr); /* Normally if we have it in the pack then we do not bother writing * it out into .git/objects/??/?{38} file. @@@ -3163,8 -3116,7 +3152,8 @@@ int hash_sha1_file_literally(const voi int hdrlen, status = 0; /* type string, SP, %lu of the length plus NUL must fit this */ - header = xmalloc(strlen(type) + 32); + hdrlen = strlen(type) + 32; + header = xmalloc(hdrlen); write_sha1_file_prepare(buf, len, type, sha1, header, &hdrlen); if (!(flags & HASH_WRITE_OBJECT)) @@@ -3192,7 -3144,7 +3181,7 @@@ int force_object_loose(const unsigned c buf = read_packed_sha1(sha1, &type, &len); if (!buf) return error("cannot read sha1_file for %s", sha1_to_hex(sha1)); - hdrlen = sprintf(hdr, "%s %lu", typename(type), len) + 1; + hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(type), len) + 1; ret = write_loose_object(sha1, hdr, hdrlen, buf, len, mtime); free(buf);