From: Junio C Hamano Date: Mon, 25 Sep 2017 06:24:06 +0000 (+0900) Subject: Merge branch 'jk/write-in-full-fix' X-Git-Tag: v2.15.0-rc0~69 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/c50424a6f07f17ff9b06927606df650cd73a09a3?hp=-c Merge branch 'jk/write-in-full-fix' Many codepaths did not diagnose write failures correctly when disks go full, due to their misuse of write_in_full() helper function, which have been corrected. * jk/write-in-full-fix: read_pack_header: handle signed/unsigned comparison in read result config: flip return value of store_write_*() notes-merge: use ssize_t for write_in_full() return value pkt-line: check write_in_full() errors against "< 0" convert less-trivial versions of "write_in_full() != len" avoid "write_in_full(fd, buf, len) != len" pattern get-tar-commit-id: check write_in_full() return against 0 config: avoid "write_in_full(fd, buf, len) < len" pattern --- c50424a6f07f17ff9b06927606df650cd73a09a3 diff --combined builtin/receive-pack.c index 52c63ebfdc,01dea59f58..dd06b3fb4f --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@@ -23,7 -23,6 +23,7 @@@ #include "fsck.h" #include "tmp-objdir.h" #include "oidset.h" +#include "packfile.h" static const char * const receive_pack_usage[] = { N_("git receive-pack "), @@@ -743,7 -742,7 +743,7 @@@ static int run_and_feed_hook(const cha size_t n; if (feed(feed_state, &buf, &n)) break; - if (write_in_full(proc.in, buf, n) != n) + if (write_in_full(proc.in, buf, n) < 0) break; } close(proc.in); @@@ -920,9 -919,9 +920,9 @@@ static int update_shallow_ref(struct co */ static int head_has_history(void) { - unsigned char sha1[20]; + struct object_id oid; - return !get_sha1("HEAD", sha1); + return !get_oid("HEAD", &oid); } static const char *push_to_deploy(unsigned char *sha1, @@@ -1139,7 -1138,7 +1139,7 @@@ static const char *update(struct comman } if (ref_transaction_delete(transaction, namespaced_name, - old_oid->hash, + old_oid ? old_oid->hash : NULL, 0, "push", &err)) { rp_error("%s", err.buf); strbuf_release(&err); diff --combined builtin/unpack-file.c index 281ca1db6c,672a54fcdf..32e0155577 --- a/builtin/unpack-file.c +++ b/builtin/unpack-file.c @@@ -1,7 -1,7 +1,7 @@@ #include "builtin.h" #include "config.h" -static char *create_temp_file(unsigned char *sha1) +static char *create_temp_file(struct object_id *oid) { static char path[50]; void *buf; @@@ -9,13 -9,13 +9,13 @@@ unsigned long size; int fd; - buf = read_sha1_file(sha1, &type, &size); + buf = read_sha1_file(oid->hash, &type, &size); if (!buf || type != OBJ_BLOB) - die("unable to read blob object %s", sha1_to_hex(sha1)); + die("unable to read blob object %s", oid_to_hex(oid)); xsnprintf(path, sizeof(path), ".merge_file_XXXXXX"); fd = xmkstemp(path); - if (write_in_full(fd, buf, size) != size) + if (write_in_full(fd, buf, size) < 0) die_errno("unable to write temp-file"); close(fd); return path; @@@ -23,15 -23,15 +23,15 @@@ int cmd_unpack_file(int argc, const char **argv, const char *prefix) { - unsigned char sha1[20]; + struct object_id oid; if (argc != 2 || !strcmp(argv[1], "-h")) usage("git unpack-file "); - if (get_sha1(argv[1], sha1)) + if (get_oid(argv[1], &oid)) die("Not a valid object name %s", argv[1]); git_config(git_default_config, NULL); - puts(create_temp_file(sha1)); + puts(create_temp_file(&oid)); return 0; } diff --combined config.c index cd5a69e630,d70fe71273..a77cae56ed --- a/config.c +++ b/config.c @@@ -929,7 -929,7 +929,7 @@@ ssize_t git_config_ssize_t(const char * return ret; } -int git_parse_maybe_bool(const char *value) +static int git_parse_maybe_bool_text(const char *value) { if (!value) return 1; @@@ -946,9 -946,9 +946,9 @@@ return -1; } -int git_config_maybe_bool(const char *name, const char *value) +int git_parse_maybe_bool(const char *value) { - int v = git_parse_maybe_bool(value); + int v = git_parse_maybe_bool_text(value); if (0 <= v) return v; if (git_parse_int(value, &v)) @@@ -958,7 -958,7 +958,7 @@@ int git_config_bool_or_int(const char *name, const char *value, int *is_bool) { - int v = git_parse_maybe_bool(value); + int v = git_parse_maybe_bool_text(value); if (0 <= v) { *is_bool = 1; return v; @@@ -1464,9 -1464,9 +1464,9 @@@ int git_config_from_mem(config_fn_t fn return do_config_from(&top, fn, data); } -int git_config_from_blob_sha1(config_fn_t fn, +int git_config_from_blob_oid(config_fn_t fn, const char *name, - const unsigned char *sha1, + const struct object_id *oid, void *data) { enum object_type type; @@@ -1474,7 -1474,7 +1474,7 @@@ unsigned long size; int ret; - buf = read_sha1_file(sha1, &type, &size); + buf = read_sha1_file(oid->hash, &type, &size); if (!buf) return error("unable to load config blob object '%s'", name); if (type != OBJ_BLOB) { @@@ -1492,11 -1492,11 +1492,11 @@@ static int git_config_from_blob_ref(con const char *name, void *data) { - unsigned char sha1[20]; + struct object_id oid; - if (get_sha1(name, sha1) < 0) + if (get_oid(name, &oid) < 0) return error("unable to resolve config blob '%s'", name); - return git_config_from_blob_sha1(fn, name, sha1, data); + return git_config_from_blob_oid(fn, name, &oid, data); } const char *git_etc_gitconfig(void) @@@ -1719,19 -1719,17 +1719,19 @@@ static int configset_add_value(struct c } static int config_set_element_cmp(const void *unused_cmp_data, - const struct config_set_element *e1, - const struct config_set_element *e2, + const void *entry, + const void *entry_or_key, const void *unused_keydata) { + const struct config_set_element *e1 = entry; + const struct config_set_element *e2 = entry_or_key; + return strcmp(e1->key, e2->key); } void git_configset_init(struct config_set *cs) { - hashmap_init(&cs->config_hash, (hashmap_cmp_fn)config_set_element_cmp, - NULL, 0); + hashmap_init(&cs->config_hash, config_set_element_cmp, NULL, 0); cs->hash_initialized = 1; cs->list.nr = 0; cs->list.alloc = 0; @@@ -1852,7 -1850,7 +1852,7 @@@ int git_configset_get_maybe_bool(struc { const char *value; if (!git_configset_get_value(cs, key, &value)) { - *dest = git_config_maybe_bool(key, value); + *dest = git_parse_maybe_bool(value); if (*dest == -1) return -1; return 0; @@@ -2059,23 -2057,6 +2059,23 @@@ int git_config_get_pathname(const char return repo_config_get_pathname(the_repository, key, dest); } +/* + * Note: This function exists solely to maintain backward compatibility with + * 'fetch' and 'update_clone' storing configuration in '.gitmodules' and should + * NOT be used anywhere else. + * + * Runs the provided config function on the '.gitmodules' file found in the + * working directory. + */ +void config_from_gitmodules(config_fn_t fn, void *data) +{ + if (the_repository->worktree) { + char *file = repo_worktree_path(the_repository, GITMODULES_FILE); + git_config_from_file(fn, file, data); + free(file); + } +} + int git_config_get_expiry(const char *key, const char **output) { int ret = git_config_get_string_const(key, output); @@@ -2089,28 -2070,6 +2089,28 @@@ return ret; } +int git_config_get_expiry_in_days(const char *key, timestamp_t *expiry, timestamp_t now) +{ + char *expiry_string; + intmax_t days; + timestamp_t when; + + if (git_config_get_string(key, &expiry_string)) + return 1; /* no such thing */ + + if (git_parse_signed(expiry_string, &days, maximum_signed_value_of_type(int))) { + const int scale = 86400; + *expiry = now - days * scale; + return 0; + } + + if (!parse_expiry_date(expiry_string, &when)) { + *expiry = when; + return 0; + } + return -1; /* thing exists but cannot be parsed */ +} + int git_config_get_untracked_cache(void) { int val = -1; @@@ -2292,10 -2251,11 +2292,11 @@@ static int write_error(const char *file return 4; } - static int store_write_section(int fd, const char *key) + static ssize_t write_section(int fd, const char *key) { const char *dot; - int i, success; + int i; + ssize_t ret; struct strbuf sb = STRBUF_INIT; dot = memchr(key, '.', store.baselen); @@@ -2311,15 -2271,16 +2312,16 @@@ strbuf_addf(&sb, "[%.*s]\n", store.baselen, key); } - success = write_in_full(fd, sb.buf, sb.len) == sb.len; + ret = write_in_full(fd, sb.buf, sb.len); strbuf_release(&sb); - return success; + return ret; } - static int store_write_pair(int fd, const char *key, const char *value) + static ssize_t write_pair(int fd, const char *key, const char *value) { - int i, success; + int i; + ssize_t ret; int length = strlen(key + store.baselen + 1); const char *quote = ""; struct strbuf sb = STRBUF_INIT; @@@ -2359,10 -2320,10 +2361,10 @@@ } strbuf_addf(&sb, "%s\n", quote); - success = write_in_full(fd, sb.buf, sb.len) == sb.len; + ret = write_in_full(fd, sb.buf, sb.len); strbuf_release(&sb); - return success; + return ret; } static ssize_t find_beginning_of_line(const char *contents, size_t size, @@@ -2445,7 -2406,7 +2447,7 @@@ int git_config_set_multivar_in_file_gen { int fd = -1, in_fd = -1; int ret; - struct lock_file *lock = NULL; + struct lock_file lock = LOCK_INIT; char *filename_buf = NULL; char *contents = NULL; size_t contents_sz; @@@ -2464,7 -2425,8 +2466,7 @@@ * The lock serves a purpose in addition to locking: the new * contents of .git/config will be written into it. */ - lock = xcalloc(1, sizeof(struct lock_file)); - fd = hold_lock_file_for_update(lock, config_filename, 0); + fd = hold_lock_file_for_update(&lock, config_filename, 0); if (fd < 0) { error_errno("could not lock config file %s", config_filename); free(store.key); @@@ -2491,8 -2453,8 +2493,8 @@@ } store.key = (char *)key; - if (!store_write_section(fd, key) || - !store_write_pair(fd, key, value)) + if (write_section(fd, key) < 0 || + write_pair(fd, key, value) < 0) goto write_err_out; } else { struct stat st; @@@ -2577,8 -2539,8 +2579,8 @@@ close(in_fd); in_fd = -1; - if (chmod(get_lock_file_path(lock), st.st_mode & 07777) < 0) { - error_errno("chmod on %s failed", get_lock_file_path(lock)); + if (chmod(get_lock_file_path(&lock), st.st_mode & 07777) < 0) { + error_errno("chmod on %s failed", get_lock_file_path(&lock)); ret = CONFIG_NO_WRITE; goto out_free; } @@@ -2602,11 -2564,10 +2604,10 @@@ /* write the first part of the config */ if (copy_end > copy_begin) { if (write_in_full(fd, contents + copy_begin, - copy_end - copy_begin) < - copy_end - copy_begin) + copy_end - copy_begin) < 0) goto write_err_out; if (new_line && - write_str_in_full(fd, "\n") != 1) + write_str_in_full(fd, "\n") < 0) goto write_err_out; } copy_begin = store.offset[i]; @@@ -2615,37 -2576,45 +2616,36 @@@ /* write the pair (value == NULL means unset) */ if (value != NULL) { if (store.state == START) { - if (!store_write_section(fd, key)) + if (write_section(fd, key) < 0) goto write_err_out; } - if (!store_write_pair(fd, key, value)) + if (write_pair(fd, key, value) < 0) goto write_err_out; } /* write the rest of the config */ if (copy_begin < contents_sz) if (write_in_full(fd, contents + copy_begin, - contents_sz - copy_begin) < - contents_sz - copy_begin) + contents_sz - copy_begin) < 0) goto write_err_out; munmap(contents, contents_sz); contents = NULL; } - if (commit_lock_file(lock) < 0) { + if (commit_lock_file(&lock) < 0) { error_errno("could not write config file %s", config_filename); ret = CONFIG_NO_WRITE; - lock = NULL; goto out_free; } - /* - * lock is committed, so don't try to roll it back below. - * NOTE: Since lockfile.c keeps a linked list of all created - * lock_file structures, it isn't safe to free(lock). It's - * better to just leave it hanging around. - */ - lock = NULL; ret = 0; /* Invalidate the config cache */ git_config_clear(); out_free: - if (lock) - rollback_lock_file(lock); + rollback_lock_file(&lock); free(filename_buf); if (contents) munmap(contents, contents_sz); @@@ -2654,7 -2623,7 +2654,7 @@@ return ret; write_err_out: - ret = write_error(get_lock_file_path(lock)); + ret = write_error(get_lock_file_path(&lock)); goto out_free; } @@@ -2803,7 -2772,7 +2803,7 @@@ int git_config_rename_section_in_file(c continue; } store.baselen = strlen(new_name); - if (!store_write_section(out_fd, new_name)) { + if (write_section(out_fd, new_name) < 0) { ret = write_error(get_lock_file_path(lock)); goto out; } @@@ -2829,7 -2798,7 +2829,7 @@@ if (remove) continue; length = strlen(output); - if (write_in_full(out_fd, output, length) != length) { + if (write_in_full(out_fd, output, length) < 0) { ret = write_error(get_lock_file_path(lock)); goto out; } diff --combined diff.c index ea7e5978bc,6f58bca2f9..3c6a3e0faa --- a/diff.c +++ b/diff.c @@@ -16,12 -16,10 +16,12 @@@ #include "userdiff.h" #include "submodule-config.h" #include "submodule.h" +#include "hashmap.h" #include "ll-merge.h" #include "string-list.h" #include "argv-array.h" #include "graph.h" +#include "packfile.h" #ifdef NO_FAST_WORKING_DIRECTORY #define FAST_WORKING_DIRECTORY 0 @@@ -34,7 -32,6 +34,7 @@@ static int diff_indent_heuristic = 1 static int diff_rename_limit_default = 400; static int diff_suppress_blank_empty; static int diff_use_color_default = -1; +static int diff_color_moved_default; static int diff_context_default = 3; static int diff_interhunk_context_default; static const char *diff_word_regex_cfg; @@@ -59,14 -56,6 +59,14 @@@ static char diff_colors[][COLOR_MAXLEN GIT_COLOR_YELLOW, /* COMMIT */ GIT_COLOR_BG_RED, /* WHITESPACE */ GIT_COLOR_NORMAL, /* FUNCINFO */ + GIT_COLOR_BOLD_MAGENTA, /* OLD_MOVED */ + GIT_COLOR_BOLD_BLUE, /* OLD_MOVED ALTERNATIVE */ + GIT_COLOR_FAINT, /* OLD_MOVED_DIM */ + GIT_COLOR_FAINT_ITALIC, /* OLD_MOVED_ALTERNATIVE_DIM */ + GIT_COLOR_BOLD_CYAN, /* NEW_MOVED */ + GIT_COLOR_BOLD_YELLOW, /* NEW_MOVED ALTERNATIVE */ + GIT_COLOR_FAINT, /* NEW_MOVED_DIM */ + GIT_COLOR_FAINT_ITALIC, /* NEW_MOVED_ALTERNATIVE_DIM */ }; static NORETURN void die_want_option(const char *option_name) @@@ -92,22 -81,6 +92,22 @@@ static int parse_diff_color_slot(const return DIFF_WHITESPACE; if (!strcasecmp(var, "func")) return DIFF_FUNCINFO; + if (!strcasecmp(var, "oldmoved")) + return DIFF_FILE_OLD_MOVED; + if (!strcasecmp(var, "oldmovedalternative")) + return DIFF_FILE_OLD_MOVED_ALT; + if (!strcasecmp(var, "oldmoveddimmed")) + return DIFF_FILE_OLD_MOVED_DIM; + if (!strcasecmp(var, "oldmovedalternativedimmed")) + return DIFF_FILE_OLD_MOVED_ALT_DIM; + if (!strcasecmp(var, "newmoved")) + return DIFF_FILE_NEW_MOVED; + if (!strcasecmp(var, "newmovedalternative")) + return DIFF_FILE_NEW_MOVED_ALT; + if (!strcasecmp(var, "newmoveddimmed")) + return DIFF_FILE_NEW_MOVED_DIM; + if (!strcasecmp(var, "newmovedalternativedimmed")) + return DIFF_FILE_NEW_MOVED_ALT_DIM; return -1; } @@@ -256,44 -229,12 +256,44 @@@ int git_diff_heuristic_config(const cha return 0; } +static int parse_color_moved(const char *arg) +{ + switch (git_parse_maybe_bool(arg)) { + case 0: + return COLOR_MOVED_NO; + case 1: + return COLOR_MOVED_DEFAULT; + default: + break; + } + + if (!strcmp(arg, "no")) + return COLOR_MOVED_NO; + else if (!strcmp(arg, "plain")) + return COLOR_MOVED_PLAIN; + else if (!strcmp(arg, "zebra")) + return COLOR_MOVED_ZEBRA; + else if (!strcmp(arg, "default")) + return COLOR_MOVED_DEFAULT; + else if (!strcmp(arg, "dimmed_zebra")) + return COLOR_MOVED_ZEBRA_DIM; + else + return error(_("color moved setting must be one of 'no', 'default', 'zebra', 'dimmed_zebra', 'plain'")); +} + int git_diff_ui_config(const char *var, const char *value, void *cb) { if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff")) { diff_use_color_default = git_config_colorbool(var, value); return 0; } + if (!strcmp(var, "diff.colormoved")) { + int cm = parse_color_moved(value); + if (cm < 0) + return -1; + diff_color_moved_default = cm; + return 0; + } if (!strcmp(var, "diff.context")) { diff_context_default = git_config_int(var, value); if (diff_context_default < 0) @@@ -402,6 -343,9 +402,6 @@@ int git_diff_basic_config(const char *v return 0; } - if (starts_with(var, "submodule.")) - return parse_submodule_config_option(var, value); - if (git_diff_heuristic_config(var, value, cb) < 0) return -1; @@@ -459,9 -403,11 +459,9 @@@ static struct diff_tempfile * If this diff_tempfile instance refers to a temporary file, * this tempfile object is used to manage its lifetime. */ - struct tempfile tempfile; + struct tempfile *tempfile; } diff_temp[2]; -typedef unsigned long (*sane_truncate_fn)(char *line, unsigned long len); - struct emit_callback { int color_diff; unsigned ws_rule; @@@ -469,6 -415,7 +469,6 @@@ int blank_at_eof_in_postimage; int lno_in_preimage; int lno_in_postimage; - sane_truncate_fn truncate; const char **label_path; struct diff_words_data *diff_words; struct diff_options *opt; @@@ -610,735 -557,68 +610,735 @@@ static void emit_line(struct diff_optio emit_line_0(o, set, reset, line[0], line+1, len-1); } -static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len) +enum diff_symbol { + DIFF_SYMBOL_BINARY_DIFF_HEADER, + DIFF_SYMBOL_BINARY_DIFF_HEADER_DELTA, + DIFF_SYMBOL_BINARY_DIFF_HEADER_LITERAL, + DIFF_SYMBOL_BINARY_DIFF_BODY, + DIFF_SYMBOL_BINARY_DIFF_FOOTER, + DIFF_SYMBOL_STATS_SUMMARY_NO_FILES, + DIFF_SYMBOL_STATS_SUMMARY_ABBREV, + DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES, + DIFF_SYMBOL_STATS_LINE, + DIFF_SYMBOL_WORD_DIFF, + DIFF_SYMBOL_STAT_SEP, + DIFF_SYMBOL_SUMMARY, + DIFF_SYMBOL_SUBMODULE_ADD, + DIFF_SYMBOL_SUBMODULE_DEL, + DIFF_SYMBOL_SUBMODULE_UNTRACKED, + DIFF_SYMBOL_SUBMODULE_MODIFIED, + DIFF_SYMBOL_SUBMODULE_HEADER, + DIFF_SYMBOL_SUBMODULE_ERROR, + DIFF_SYMBOL_SUBMODULE_PIPETHROUGH, + DIFF_SYMBOL_REWRITE_DIFF, + DIFF_SYMBOL_BINARY_FILES, + DIFF_SYMBOL_HEADER, + DIFF_SYMBOL_FILEPAIR_PLUS, + DIFF_SYMBOL_FILEPAIR_MINUS, + DIFF_SYMBOL_WORDS_PORCELAIN, + DIFF_SYMBOL_WORDS, + DIFF_SYMBOL_CONTEXT, + DIFF_SYMBOL_CONTEXT_INCOMPLETE, + DIFF_SYMBOL_PLUS, + DIFF_SYMBOL_MINUS, + DIFF_SYMBOL_NO_LF_EOF, + DIFF_SYMBOL_CONTEXT_FRAGINFO, + DIFF_SYMBOL_CONTEXT_MARKER, + DIFF_SYMBOL_SEPARATOR +}; +/* + * Flags for content lines: + * 0..12 are whitespace rules + * 13-15 are WSEH_NEW | WSEH_OLD | WSEH_CONTEXT + * 16 is marking if the line is blank at EOF + */ +#define DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF (1<<16) +#define DIFF_SYMBOL_MOVED_LINE (1<<17) +#define DIFF_SYMBOL_MOVED_LINE_ALT (1<<18) +#define DIFF_SYMBOL_MOVED_LINE_UNINTERESTING (1<<19) +#define DIFF_SYMBOL_CONTENT_WS_MASK (WSEH_NEW | WSEH_OLD | WSEH_CONTEXT | WS_RULE_MASK) + +/* + * This struct is used when we need to buffer the output of the diff output. + * + * NEEDSWORK: Instead of storing a copy of the line, add an offset pointer + * into the pre/post image file. This pointer could be a union with the + * line pointer. By storing an offset into the file instead of the literal line, + * we can decrease the memory footprint for the buffered output. At first we + * may want to only have indirection for the content lines, but we could also + * enhance the state for emitting prefabricated lines, e.g. the similarity + * score line or hunk/file headers would only need to store a number or path + * and then the output can be constructed later on depending on state. + */ +struct emitted_diff_symbol { + const char *line; + int len; + int flags; + enum diff_symbol s; +}; +#define EMITTED_DIFF_SYMBOL_INIT {NULL} + +struct emitted_diff_symbols { + struct emitted_diff_symbol *buf; + int nr, alloc; +}; +#define EMITTED_DIFF_SYMBOLS_INIT {NULL, 0, 0} + +static void append_emitted_diff_symbol(struct diff_options *o, + struct emitted_diff_symbol *e) { - if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) && - ecbdata->blank_at_eof_in_preimage && - ecbdata->blank_at_eof_in_postimage && - ecbdata->blank_at_eof_in_preimage <= ecbdata->lno_in_preimage && - ecbdata->blank_at_eof_in_postimage <= ecbdata->lno_in_postimage)) - return 0; - return ws_blank_line(line, len, ecbdata->ws_rule); + struct emitted_diff_symbol *f; + + ALLOC_GROW(o->emitted_symbols->buf, + o->emitted_symbols->nr + 1, + o->emitted_symbols->alloc); + f = &o->emitted_symbols->buf[o->emitted_symbols->nr++]; + + memcpy(f, e, sizeof(struct emitted_diff_symbol)); + f->line = e->line ? xmemdupz(e->line, e->len) : NULL; } -static void emit_line_checked(const char *reset, - struct emit_callback *ecbdata, - const char *line, int len, - enum color_diff color, - unsigned ws_error_highlight, - char sign) +struct moved_entry { + struct hashmap_entry ent; + const struct emitted_diff_symbol *es; + struct moved_entry *next_line; +}; + +static int next_byte(const char **cp, const char **endp, + const struct diff_options *diffopt) +{ + int retval; + + if (*cp > *endp) + return -1; + + if (DIFF_XDL_TST(diffopt, IGNORE_WHITESPACE_CHANGE)) { + while (*cp < *endp && isspace(**cp)) + (*cp)++; + /* + * After skipping a couple of whitespaces, we still have to + * account for one space. + */ + return (int)' '; + } + + if (DIFF_XDL_TST(diffopt, IGNORE_WHITESPACE)) { + while (*cp < *endp && isspace(**cp)) + (*cp)++; + /* return the first non-ws character via the usual below */ + } + + retval = (unsigned char)(**cp); + (*cp)++; + return retval; +} + +static int moved_entry_cmp(const struct diff_options *diffopt, + const struct moved_entry *a, + const struct moved_entry *b, + const void *keydata) +{ + const char *ap = a->es->line, *ae = a->es->line + a->es->len; + const char *bp = b->es->line, *be = b->es->line + b->es->len; + + if (!(diffopt->xdl_opts & XDF_WHITESPACE_FLAGS)) + return a->es->len != b->es->len || memcmp(ap, bp, a->es->len); + + if (DIFF_XDL_TST(diffopt, IGNORE_WHITESPACE_AT_EOL)) { + while (ae > ap && isspace(*ae)) + ae--; + while (be > bp && isspace(*be)) + be--; + } + + while (1) { + int ca, cb; + ca = next_byte(&ap, &ae, diffopt); + cb = next_byte(&bp, &be, diffopt); + if (ca != cb) + return 1; + if (ca < 0) + return 0; + } +} + +static unsigned get_string_hash(struct emitted_diff_symbol *es, struct diff_options *o) +{ + if (o->xdl_opts & XDF_WHITESPACE_FLAGS) { + static struct strbuf sb = STRBUF_INIT; + const char *ap = es->line, *ae = es->line + es->len; + int c; + + strbuf_reset(&sb); + while (ae > ap && isspace(*ae)) + ae--; + while ((c = next_byte(&ap, &ae, o)) > 0) + strbuf_addch(&sb, c); + + return memhash(sb.buf, sb.len); + } else { + return memhash(es->line, es->len); + } +} + +static struct moved_entry *prepare_entry(struct diff_options *o, + int line_no) +{ + struct moved_entry *ret = xmalloc(sizeof(*ret)); + struct emitted_diff_symbol *l = &o->emitted_symbols->buf[line_no]; + + ret->ent.hash = get_string_hash(l, o); + ret->es = l; + ret->next_line = NULL; + + return ret; +} + +static void add_lines_to_move_detection(struct diff_options *o, + struct hashmap *add_lines, + struct hashmap *del_lines) +{ + struct moved_entry *prev_line = NULL; + + int n; + for (n = 0; n < o->emitted_symbols->nr; n++) { + struct hashmap *hm; + struct moved_entry *key; + + switch (o->emitted_symbols->buf[n].s) { + case DIFF_SYMBOL_PLUS: + hm = add_lines; + break; + case DIFF_SYMBOL_MINUS: + hm = del_lines; + break; + default: + prev_line = NULL; + continue; + } + + key = prepare_entry(o, n); + if (prev_line && prev_line->es->s == o->emitted_symbols->buf[n].s) + prev_line->next_line = key; + + hashmap_add(hm, key); + prev_line = key; + } +} + +static int shrink_potential_moved_blocks(struct moved_entry **pmb, + int pmb_nr) +{ + int lp, rp; + + /* Shrink the set of potential block to the remaining running */ + for (lp = 0, rp = pmb_nr - 1; lp <= rp;) { + while (lp < pmb_nr && pmb[lp]) + lp++; + /* lp points at the first NULL now */ + + while (rp > -1 && !pmb[rp]) + rp--; + /* rp points at the last non-NULL */ + + if (lp < pmb_nr && rp > -1 && lp < rp) { + pmb[lp] = pmb[rp]; + pmb[rp] = NULL; + rp--; + lp++; + } + } + + /* Remember the number of running sets */ + return rp + 1; +} + +/* + * If o->color_moved is COLOR_MOVED_PLAIN, this function does nothing. + * + * Otherwise, if the last block has fewer alphanumeric characters than + * COLOR_MOVED_MIN_ALNUM_COUNT, unset DIFF_SYMBOL_MOVED_LINE on all lines in + * that block. + * + * The last block consists of the (n - block_length)'th line up to but not + * including the nth line. + * + * NEEDSWORK: This uses the same heuristic as blame_entry_score() in blame.c. + * Think of a way to unify them. + */ +static void adjust_last_block(struct diff_options *o, int n, int block_length) +{ + int i, alnum_count = 0; + if (o->color_moved == COLOR_MOVED_PLAIN) + return; + for (i = 1; i < block_length + 1; i++) { + const char *c = o->emitted_symbols->buf[n - i].line; + for (; *c; c++) { + if (!isalnum(*c)) + continue; + alnum_count++; + if (alnum_count >= COLOR_MOVED_MIN_ALNUM_COUNT) + return; + } + } + for (i = 1; i < block_length + 1; i++) + o->emitted_symbols->buf[n - i].flags &= ~DIFF_SYMBOL_MOVED_LINE; +} + +/* Find blocks of moved code, delegate actual coloring decision to helper */ +static void mark_color_as_moved(struct diff_options *o, + struct hashmap *add_lines, + struct hashmap *del_lines) +{ + struct moved_entry **pmb = NULL; /* potentially moved blocks */ + int pmb_nr = 0, pmb_alloc = 0; + int n, flipped_block = 1, block_length = 0; + + + for (n = 0; n < o->emitted_symbols->nr; n++) { + struct hashmap *hm = NULL; + struct moved_entry *key; + struct moved_entry *match = NULL; + struct emitted_diff_symbol *l = &o->emitted_symbols->buf[n]; + int i; + + switch (l->s) { + case DIFF_SYMBOL_PLUS: + hm = del_lines; + key = prepare_entry(o, n); + match = hashmap_get(hm, key, o); + free(key); + break; + case DIFF_SYMBOL_MINUS: + hm = add_lines; + key = prepare_entry(o, n); + match = hashmap_get(hm, key, o); + free(key); + break; + default: + flipped_block = 1; + } + + if (!match) { + adjust_last_block(o, n, block_length); + pmb_nr = 0; + block_length = 0; + continue; + } + + l->flags |= DIFF_SYMBOL_MOVED_LINE; + + if (o->color_moved == COLOR_MOVED_PLAIN) + continue; + + /* Check any potential block runs, advance each or nullify */ + for (i = 0; i < pmb_nr; i++) { + struct moved_entry *p = pmb[i]; + struct moved_entry *pnext = (p && p->next_line) ? + p->next_line : NULL; + if (pnext && !hm->cmpfn(o, pnext, match, NULL)) { + pmb[i] = p->next_line; + } else { + pmb[i] = NULL; + } + } + + pmb_nr = shrink_potential_moved_blocks(pmb, pmb_nr); + + if (pmb_nr == 0) { + /* + * The current line is the start of a new block. + * Setup the set of potential blocks. + */ + for (; match; match = hashmap_get_next(hm, match)) { + ALLOC_GROW(pmb, pmb_nr + 1, pmb_alloc); + pmb[pmb_nr++] = match; + } + + flipped_block = (flipped_block + 1) % 2; + + adjust_last_block(o, n, block_length); + block_length = 0; + } + + block_length++; + + if (flipped_block) + l->flags |= DIFF_SYMBOL_MOVED_LINE_ALT; + } + adjust_last_block(o, n, block_length); + + free(pmb); +} + +#define DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK \ + (DIFF_SYMBOL_MOVED_LINE | DIFF_SYMBOL_MOVED_LINE_ALT) +static void dim_moved_lines(struct diff_options *o) +{ + int n; + for (n = 0; n < o->emitted_symbols->nr; n++) { + struct emitted_diff_symbol *prev = (n != 0) ? + &o->emitted_symbols->buf[n - 1] : NULL; + struct emitted_diff_symbol *l = &o->emitted_symbols->buf[n]; + struct emitted_diff_symbol *next = + (n < o->emitted_symbols->nr - 1) ? + &o->emitted_symbols->buf[n + 1] : NULL; + + /* Not a plus or minus line? */ + if (l->s != DIFF_SYMBOL_PLUS && l->s != DIFF_SYMBOL_MINUS) + continue; + + /* Not a moved line? */ + if (!(l->flags & DIFF_SYMBOL_MOVED_LINE)) + continue; + + /* + * If prev or next are not a plus or minus line, + * pretend they don't exist + */ + if (prev && prev->s != DIFF_SYMBOL_PLUS && + prev->s != DIFF_SYMBOL_MINUS) + prev = NULL; + if (next && next->s != DIFF_SYMBOL_PLUS && + next->s != DIFF_SYMBOL_MINUS) + next = NULL; + + /* Inside a block? */ + if ((prev && + (prev->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK) == + (l->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK)) && + (next && + (next->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK) == + (l->flags & DIFF_SYMBOL_MOVED_LINE_ZEBRA_MASK))) { + l->flags |= DIFF_SYMBOL_MOVED_LINE_UNINTERESTING; + continue; + } + + /* Check if we are at an interesting bound: */ + if (prev && (prev->flags & DIFF_SYMBOL_MOVED_LINE) && + (prev->flags & DIFF_SYMBOL_MOVED_LINE_ALT) != + (l->flags & DIFF_SYMBOL_MOVED_LINE_ALT)) + continue; + if (next && (next->flags & DIFF_SYMBOL_MOVED_LINE) && + (next->flags & DIFF_SYMBOL_MOVED_LINE_ALT) != + (l->flags & DIFF_SYMBOL_MOVED_LINE_ALT)) + continue; + + /* + * The boundary to prev and next are not interesting, + * so this line is not interesting as a whole + */ + l->flags |= DIFF_SYMBOL_MOVED_LINE_UNINTERESTING; + } +} + +static void emit_line_ws_markup(struct diff_options *o, + const char *set, const char *reset, + const char *line, int len, char sign, + unsigned ws_rule, int blank_at_eof) { - const char *set = diff_get_color(ecbdata->color_diff, color); const char *ws = NULL; - if (ecbdata->opt->ws_error_highlight & ws_error_highlight) { - ws = diff_get_color(ecbdata->color_diff, DIFF_WHITESPACE); + if (o->ws_error_highlight & ws_rule) { + ws = diff_get_color_opt(o, DIFF_WHITESPACE); if (!*ws) ws = NULL; } if (!ws) - emit_line_0(ecbdata->opt, set, reset, sign, line, len); - else if (sign == '+' && new_blank_line_at_eof(ecbdata, line, len)) + emit_line_0(o, set, reset, sign, line, len); + else if (blank_at_eof) /* Blank line at EOF - paint '+' as well */ - emit_line_0(ecbdata->opt, ws, reset, sign, line, len); + emit_line_0(o, ws, reset, sign, line, len); else { /* Emit just the prefix, then the rest. */ - emit_line_0(ecbdata->opt, set, reset, sign, "", 0); - ws_check_emit(line, len, ecbdata->ws_rule, - ecbdata->opt->file, set, reset, ws); + emit_line_0(o, set, reset, sign, "", 0); + ws_check_emit(line, len, ws_rule, + o->file, set, reset, ws); } } +static void emit_diff_symbol_from_struct(struct diff_options *o, + struct emitted_diff_symbol *eds) +{ + static const char *nneof = " No newline at end of file\n"; + const char *context, *reset, *set, *meta, *fraginfo; + struct strbuf sb = STRBUF_INIT; + + enum diff_symbol s = eds->s; + const char *line = eds->line; + int len = eds->len; + unsigned flags = eds->flags; + + switch (s) { + case DIFF_SYMBOL_NO_LF_EOF: + context = diff_get_color_opt(o, DIFF_CONTEXT); + reset = diff_get_color_opt(o, DIFF_RESET); + putc('\n', o->file); + emit_line_0(o, context, reset, '\\', + nneof, strlen(nneof)); + break; + case DIFF_SYMBOL_SUBMODULE_HEADER: + case DIFF_SYMBOL_SUBMODULE_ERROR: + case DIFF_SYMBOL_SUBMODULE_PIPETHROUGH: + case DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES: + case DIFF_SYMBOL_SUMMARY: + case DIFF_SYMBOL_STATS_LINE: + case DIFF_SYMBOL_BINARY_DIFF_BODY: + case DIFF_SYMBOL_CONTEXT_FRAGINFO: + emit_line(o, "", "", line, len); + break; + case DIFF_SYMBOL_CONTEXT_INCOMPLETE: + case DIFF_SYMBOL_CONTEXT_MARKER: + context = diff_get_color_opt(o, DIFF_CONTEXT); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line(o, context, reset, line, len); + break; + case DIFF_SYMBOL_SEPARATOR: + fprintf(o->file, "%s%c", + diff_line_prefix(o), + o->line_termination); + break; + case DIFF_SYMBOL_CONTEXT: + set = diff_get_color_opt(o, DIFF_CONTEXT); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line_ws_markup(o, set, reset, line, len, ' ', + flags & (DIFF_SYMBOL_CONTENT_WS_MASK), 0); + break; + case DIFF_SYMBOL_PLUS: + switch (flags & (DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING)) { + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING: + set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED_ALT_DIM); + break; + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT: + set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED_ALT); + break; + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING: + set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED_DIM); + break; + case DIFF_SYMBOL_MOVED_LINE: + set = diff_get_color_opt(o, DIFF_FILE_NEW_MOVED); + break; + default: + set = diff_get_color_opt(o, DIFF_FILE_NEW); + } + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line_ws_markup(o, set, reset, line, len, '+', + flags & DIFF_SYMBOL_CONTENT_WS_MASK, + flags & DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF); + break; + case DIFF_SYMBOL_MINUS: + switch (flags & (DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING)) { + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING: + set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED_ALT_DIM); + break; + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_ALT: + set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED_ALT); + break; + case DIFF_SYMBOL_MOVED_LINE | + DIFF_SYMBOL_MOVED_LINE_UNINTERESTING: + set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED_DIM); + break; + case DIFF_SYMBOL_MOVED_LINE: + set = diff_get_color_opt(o, DIFF_FILE_OLD_MOVED); + break; + default: + set = diff_get_color_opt(o, DIFF_FILE_OLD); + } + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line_ws_markup(o, set, reset, line, len, '-', + flags & DIFF_SYMBOL_CONTENT_WS_MASK, 0); + break; + case DIFF_SYMBOL_WORDS_PORCELAIN: + context = diff_get_color_opt(o, DIFF_CONTEXT); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line(o, context, reset, line, len); + fputs("~\n", o->file); + break; + case DIFF_SYMBOL_WORDS: + context = diff_get_color_opt(o, DIFF_CONTEXT); + reset = diff_get_color_opt(o, DIFF_RESET); + /* + * Skip the prefix character, if any. With + * diff_suppress_blank_empty, there may be + * none. + */ + if (line[0] != '\n') { + line++; + len--; + } + emit_line(o, context, reset, line, len); + break; + case DIFF_SYMBOL_FILEPAIR_PLUS: + meta = diff_get_color_opt(o, DIFF_METAINFO); + reset = diff_get_color_opt(o, DIFF_RESET); + fprintf(o->file, "%s%s+++ %s%s%s\n", diff_line_prefix(o), meta, + line, reset, + strchr(line, ' ') ? "\t" : ""); + break; + case DIFF_SYMBOL_FILEPAIR_MINUS: + meta = diff_get_color_opt(o, DIFF_METAINFO); + reset = diff_get_color_opt(o, DIFF_RESET); + fprintf(o->file, "%s%s--- %s%s%s\n", diff_line_prefix(o), meta, + line, reset, + strchr(line, ' ') ? "\t" : ""); + break; + case DIFF_SYMBOL_BINARY_FILES: + case DIFF_SYMBOL_HEADER: + fprintf(o->file, "%s", line); + break; + case DIFF_SYMBOL_BINARY_DIFF_HEADER: + fprintf(o->file, "%sGIT binary patch\n", diff_line_prefix(o)); + break; + case DIFF_SYMBOL_BINARY_DIFF_HEADER_DELTA: + fprintf(o->file, "%sdelta %s\n", diff_line_prefix(o), line); + break; + case DIFF_SYMBOL_BINARY_DIFF_HEADER_LITERAL: + fprintf(o->file, "%sliteral %s\n", diff_line_prefix(o), line); + break; + case DIFF_SYMBOL_BINARY_DIFF_FOOTER: + fputs(diff_line_prefix(o), o->file); + fputc('\n', o->file); + break; + case DIFF_SYMBOL_REWRITE_DIFF: + fraginfo = diff_get_color(o->use_color, DIFF_FRAGINFO); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line(o, fraginfo, reset, line, len); + break; + case DIFF_SYMBOL_SUBMODULE_ADD: + set = diff_get_color_opt(o, DIFF_FILE_NEW); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line(o, set, reset, line, len); + break; + case DIFF_SYMBOL_SUBMODULE_DEL: + set = diff_get_color_opt(o, DIFF_FILE_OLD); + reset = diff_get_color_opt(o, DIFF_RESET); + emit_line(o, set, reset, line, len); + break; + case DIFF_SYMBOL_SUBMODULE_UNTRACKED: + fprintf(o->file, "%sSubmodule %s contains untracked content\n", + diff_line_prefix(o), line); + break; + case DIFF_SYMBOL_SUBMODULE_MODIFIED: + fprintf(o->file, "%sSubmodule %s contains modified content\n", + diff_line_prefix(o), line); + break; + case DIFF_SYMBOL_STATS_SUMMARY_NO_FILES: + emit_line(o, "", "", " 0 files changed\n", + strlen(" 0 files changed\n")); + break; + case DIFF_SYMBOL_STATS_SUMMARY_ABBREV: + emit_line(o, "", "", " ...\n", strlen(" ...\n")); + break; + case DIFF_SYMBOL_WORD_DIFF: + fprintf(o->file, "%.*s", len, line); + break; + case DIFF_SYMBOL_STAT_SEP: + fputs(o->stat_sep, o->file); + break; + default: + die("BUG: unknown diff symbol"); + } + strbuf_release(&sb); +} + +static void emit_diff_symbol(struct diff_options *o, enum diff_symbol s, + const char *line, int len, unsigned flags) +{ + struct emitted_diff_symbol e = {line, len, flags, s}; + + if (o->emitted_symbols) + append_emitted_diff_symbol(o, &e); + else + emit_diff_symbol_from_struct(o, &e); +} + +void diff_emit_submodule_del(struct diff_options *o, const char *line) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_DEL, line, strlen(line), 0); +} + +void diff_emit_submodule_add(struct diff_options *o, const char *line) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_ADD, line, strlen(line), 0); +} + +void diff_emit_submodule_untracked(struct diff_options *o, const char *path) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_UNTRACKED, + path, strlen(path), 0); +} + +void diff_emit_submodule_modified(struct diff_options *o, const char *path) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_MODIFIED, + path, strlen(path), 0); +} + +void diff_emit_submodule_header(struct diff_options *o, const char *header) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_HEADER, + header, strlen(header), 0); +} + +void diff_emit_submodule_error(struct diff_options *o, const char *err) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_ERROR, err, strlen(err), 0); +} + +void diff_emit_submodule_pipethrough(struct diff_options *o, + const char *line, int len) +{ + emit_diff_symbol(o, DIFF_SYMBOL_SUBMODULE_PIPETHROUGH, line, len, 0); +} + +static int new_blank_line_at_eof(struct emit_callback *ecbdata, const char *line, int len) +{ + if (!((ecbdata->ws_rule & WS_BLANK_AT_EOF) && + ecbdata->blank_at_eof_in_preimage && + ecbdata->blank_at_eof_in_postimage && + ecbdata->blank_at_eof_in_preimage <= ecbdata->lno_in_preimage && + ecbdata->blank_at_eof_in_postimage <= ecbdata->lno_in_postimage)) + return 0; + return ws_blank_line(line, len, ecbdata->ws_rule); +} + static void emit_add_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len) { - emit_line_checked(reset, ecbdata, line, len, - DIFF_FILE_NEW, WSEH_NEW, '+'); + unsigned flags = WSEH_NEW | ecbdata->ws_rule; + if (new_blank_line_at_eof(ecbdata, line, len)) + flags |= DIFF_SYMBOL_CONTENT_BLANK_LINE_EOF; + + emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_PLUS, line, len, flags); } static void emit_del_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len) { - emit_line_checked(reset, ecbdata, line, len, - DIFF_FILE_OLD, WSEH_OLD, '-'); + unsigned flags = WSEH_OLD | ecbdata->ws_rule; + emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_MINUS, line, len, flags); } static void emit_context_line(const char *reset, struct emit_callback *ecbdata, const char *line, int len) { - emit_line_checked(reset, ecbdata, line, len, - DIFF_CONTEXT, WSEH_CONTEXT, ' '); + unsigned flags = WSEH_CONTEXT | ecbdata->ws_rule; + emit_diff_symbol(ecbdata->opt, DIFF_SYMBOL_CONTEXT, line, len, flags); } static void emit_hunk_header(struct emit_callback *ecbdata, @@@ -1361,8 -641,7 +1361,8 @@@ if (len < 10 || memcmp(line, atat, 2) || !(ep = memmem(line + 2, len - 2, atat, 2))) { - emit_line(ecbdata->opt, context, reset, line, len); + emit_diff_symbol(ecbdata->opt, + DIFF_SYMBOL_CONTEXT_MARKER, line, len, 0); return; } ep += 2; /* skip over @@ */ @@@ -1396,9 -675,7 +1396,9 @@@ } strbuf_add(&msgbuf, line + len, org_len - len); - emit_line(ecbdata->opt, "", "", msgbuf.buf, msgbuf.len); + strbuf_complete_line(&msgbuf); + emit_diff_symbol(ecbdata->opt, + DIFF_SYMBOL_CONTEXT_FRAGINFO, msgbuf.buf, msgbuf.len, 0); strbuf_release(&msgbuf); } @@@ -1414,23 -691,23 +1414,23 @@@ static void remove_tempfile(void { int i; for (i = 0; i < ARRAY_SIZE(diff_temp); i++) { - if (is_tempfile_active(&diff_temp[i].tempfile)) + if (is_tempfile_active(diff_temp[i].tempfile)) delete_tempfile(&diff_temp[i].tempfile); diff_temp[i].name = NULL; } } -static void print_line_count(FILE *file, int count) +static void add_line_count(struct strbuf *out, int count) { switch (count) { case 0: - fprintf(file, "0,0"); + strbuf_addstr(out, "0,0"); break; case 1: - fprintf(file, "1"); + strbuf_addstr(out, "1"); break; default: - fprintf(file, "1,%d", count); + strbuf_addf(out, "1,%d", count); break; } } @@@ -1439,6 -716,7 +1439,6 @@@ static void emit_rewrite_lines(struct e int prefix, const char *data, int size) { const char *endp = NULL; - static const char *nneof = " No newline at end of file\n"; const char *reset = diff_get_color(ecb->color_diff, DIFF_RESET); while (0 < size) { @@@ -1456,8 -734,13 +1456,8 @@@ size -= len; data += len; } - if (!endp) { - const char *context = diff_get_color(ecb->color_diff, - DIFF_CONTEXT); - putc('\n', ecb->opt->file); - emit_line_0(ecb->opt, context, reset, '\\', - nneof, strlen(nneof)); - } + if (!endp) + emit_diff_symbol(ecb->opt, DIFF_SYMBOL_NO_LF_EOF, NULL, 0, 0); } static void emit_rewrite_diff(const char *name_a, @@@ -1469,12 -752,16 +1469,12 @@@ struct diff_options *o) { int lc_a, lc_b; - const char *name_a_tab, *name_b_tab; - const char *metainfo = diff_get_color(o->use_color, DIFF_METAINFO); - const char *fraginfo = diff_get_color(o->use_color, DIFF_FRAGINFO); - const char *reset = diff_get_color(o->use_color, DIFF_RESET); static struct strbuf a_name = STRBUF_INIT, b_name = STRBUF_INIT; const char *a_prefix, *b_prefix; char *data_one, *data_two; size_t size_one, size_two; struct emit_callback ecbdata; - const char *line_prefix = diff_line_prefix(o); + struct strbuf out = STRBUF_INIT; if (diff_mnemonic_prefix && DIFF_OPT_TST(o, REVERSE_DIFF)) { a_prefix = o->b_prefix; @@@ -1486,6 -773,8 +1486,6 @@@ name_a += (*name_a == '/'); name_b += (*name_b == '/'); - name_a_tab = strchr(name_a, ' ') ? "\t" : ""; - name_b_tab = strchr(name_b, ' ') ? "\t" : ""; strbuf_reset(&a_name); strbuf_reset(&b_name); @@@ -1512,23 -801,18 +1512,23 @@@ lc_a = count_lines(data_one, size_one); lc_b = count_lines(data_two, size_two); - fprintf(o->file, - "%s%s--- %s%s%s\n%s%s+++ %s%s%s\n%s%s@@ -", - line_prefix, metainfo, a_name.buf, name_a_tab, reset, - line_prefix, metainfo, b_name.buf, name_b_tab, reset, - line_prefix, fraginfo); + + emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_MINUS, + a_name.buf, a_name.len, 0); + emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_PLUS, + b_name.buf, b_name.len, 0); + + strbuf_addstr(&out, "@@ -"); if (!o->irreversible_delete) - print_line_count(o->file, lc_a); + add_line_count(&out, lc_a); else - fprintf(o->file, "?,?"); - fprintf(o->file, " +"); - print_line_count(o->file, lc_b); - fprintf(o->file, " @@%s\n", reset); + strbuf_addstr(&out, "?,?"); + strbuf_addstr(&out, " +"); + add_line_count(&out, lc_b); + strbuf_addstr(&out, " @@\n"); + emit_diff_symbol(o, DIFF_SYMBOL_REWRITE_DIFF, out.buf, out.len, 0); + strbuf_release(&out); + if (lc_a && !o->irreversible_delete) emit_rewrite_lines(&ecbdata, '-', data_one, size_one); if (lc_b) @@@ -1588,49 -872,37 +1588,49 @@@ struct diff_words_data struct diff_words_style *style; }; -static int fn_out_diff_words_write_helper(FILE *fp, +static int fn_out_diff_words_write_helper(struct diff_options *o, struct diff_words_style_elem *st_el, const char *newline, - size_t count, const char *buf, - const char *line_prefix) + size_t count, const char *buf) { int print = 0; + struct strbuf sb = STRBUF_INIT; while (count) { char *p = memchr(buf, '\n', count); if (print) - fputs(line_prefix, fp); + strbuf_addstr(&sb, diff_line_prefix(o)); + if (p != buf) { - if (st_el->color && fputs(st_el->color, fp) < 0) - return -1; - if (fputs(st_el->prefix, fp) < 0 || - fwrite(buf, p ? p - buf : count, 1, fp) != 1 || - fputs(st_el->suffix, fp) < 0) - return -1; - if (st_el->color && *st_el->color - && fputs(GIT_COLOR_RESET, fp) < 0) - return -1; + const char *reset = st_el->color && *st_el->color ? + GIT_COLOR_RESET : NULL; + if (st_el->color && *st_el->color) + strbuf_addstr(&sb, st_el->color); + strbuf_addstr(&sb, st_el->prefix); + strbuf_add(&sb, buf, p ? p - buf : count); + strbuf_addstr(&sb, st_el->suffix); + if (reset) + strbuf_addstr(&sb, reset); } if (!p) - return 0; - if (fputs(newline, fp) < 0) - return -1; + goto out; + + strbuf_addstr(&sb, newline); count -= p + 1 - buf; buf = p + 1; print = 1; + if (count) { + emit_diff_symbol(o, DIFF_SYMBOL_WORD_DIFF, + sb.buf, sb.len, 0); + strbuf_reset(&sb); + } } + +out: + if (sb.len) + emit_diff_symbol(o, DIFF_SYMBOL_WORD_DIFF, + sb.buf, sb.len, 0); + strbuf_release(&sb); return 0; } @@@ -1712,20 -984,24 +1712,20 @@@ static void fn_out_diff_words_aux(void fputs(line_prefix, diff_words->opt->file); } if (diff_words->current_plus != plus_begin) { - fn_out_diff_words_write_helper(diff_words->opt->file, + fn_out_diff_words_write_helper(diff_words->opt, &style->ctx, style->newline, plus_begin - diff_words->current_plus, - diff_words->current_plus, line_prefix); - if (*(plus_begin - 1) == '\n') - fputs(line_prefix, diff_words->opt->file); + diff_words->current_plus); } if (minus_begin != minus_end) { - fn_out_diff_words_write_helper(diff_words->opt->file, + fn_out_diff_words_write_helper(diff_words->opt, &style->old, style->newline, - minus_end - minus_begin, minus_begin, - line_prefix); + minus_end - minus_begin, minus_begin); } if (plus_begin != plus_end) { - fn_out_diff_words_write_helper(diff_words->opt->file, + fn_out_diff_words_write_helper(diff_words->opt, &style->new, style->newline, - plus_end - plus_begin, plus_begin, - line_prefix); + plus_end - plus_begin, plus_begin); } diff_words->current_plus = plus_end; @@@ -1819,12 -1095,11 +1819,12 @@@ static void diff_words_show(struct diff /* special case: only removal */ if (!diff_words->plus.text.size) { - fputs(line_prefix, diff_words->opt->file); - fn_out_diff_words_write_helper(diff_words->opt->file, + emit_diff_symbol(diff_words->opt, DIFF_SYMBOL_WORD_DIFF, + line_prefix, strlen(line_prefix), 0); + fn_out_diff_words_write_helper(diff_words->opt, &style->old, style->newline, diff_words->minus.text.size, - diff_words->minus.text.ptr, line_prefix); + diff_words->minus.text.ptr); diff_words->minus.text.size = 0; return; } @@@ -1847,12 -1122,12 +1847,12 @@@ if (diff_words->current_plus != diff_words->plus.text.ptr + diff_words->plus.text.size) { if (color_words_output_graph_prefix(diff_words)) - fputs(line_prefix, diff_words->opt->file); - fn_out_diff_words_write_helper(diff_words->opt->file, + emit_diff_symbol(diff_words->opt, DIFF_SYMBOL_WORD_DIFF, + line_prefix, strlen(line_prefix), 0); + fn_out_diff_words_write_helper(diff_words->opt, &style->ctx, style->newline, diff_words->plus.text.ptr + diff_words->plus.text.size - - diff_words->current_plus, diff_words->current_plus, - line_prefix); + - diff_words->current_plus, diff_words->current_plus); } diff_words->minus.text.size = diff_words->plus.text.size = 0; } @@@ -1860,29 -1135,9 +1860,29 @@@ /* In "color-words" mode, show word-diff of words accumulated in the buffer */ static void diff_words_flush(struct emit_callback *ecbdata) { + struct diff_options *wo = ecbdata->diff_words->opt; + if (ecbdata->diff_words->minus.text.size || ecbdata->diff_words->plus.text.size) diff_words_show(ecbdata->diff_words); + + if (wo->emitted_symbols) { + struct diff_options *o = ecbdata->opt; + struct emitted_diff_symbols *wol = wo->emitted_symbols; + int i; + + /* + * NEEDSWORK: + * Instead of appending each, concat all words to a line? + */ + for (i = 0; i < wol->nr; i++) + append_emitted_diff_symbol(o, &wol->buf[i]); + + for (i = 0; i < wol->nr; i++) + free((void *)wol->buf[i].line); + + wol->nr = 0; + } } static void diff_filespec_load_driver(struct diff_filespec *one) @@@ -1918,11 -1173,6 +1918,11 @@@ static void init_diff_words_data(struc xcalloc(1, sizeof(struct diff_words_data)); ecbdata->diff_words->type = o->word_diff; ecbdata->diff_words->opt = o; + + if (orig_opts->emitted_symbols) + o->emitted_symbols = + xcalloc(1, sizeof(struct emitted_diff_symbols)); + if (!o->word_regex) o->word_regex = userdiff_word_regex(one); if (!o->word_regex) @@@ -1957,7 -1207,6 +1957,7 @@@ static void free_diff_words_data(struc { if (ecbdata->diff_words) { diff_words_flush(ecbdata); + free (ecbdata->diff_words->opt->emitted_symbols); free (ecbdata->diff_words->opt); free (ecbdata->diff_words->minus.text.ptr); free (ecbdata->diff_words->minus.orig); @@@ -1994,6 -1243,8 +1994,6 @@@ static unsigned long sane_truncate_line unsigned long allot; size_t l = len; - if (ecb->truncate) - return ecb->truncate(line, len); cp = line; allot = l; while (0 < l) { @@@ -2022,25 -1273,30 +2022,25 @@@ static void find_lno(const char *line, static void fn_out_consume(void *priv, char *line, unsigned long len) { struct emit_callback *ecbdata = priv; - const char *meta = diff_get_color(ecbdata->color_diff, DIFF_METAINFO); - const char *context = diff_get_color(ecbdata->color_diff, DIFF_CONTEXT); const char *reset = diff_get_color(ecbdata->color_diff, DIFF_RESET); struct diff_options *o = ecbdata->opt; - const char *line_prefix = diff_line_prefix(o); o->found_changes = 1; if (ecbdata->header) { - fprintf(o->file, "%s", ecbdata->header->buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + ecbdata->header->buf, ecbdata->header->len, 0); strbuf_reset(ecbdata->header); ecbdata->header = NULL; } if (ecbdata->label_path[0]) { - const char *name_a_tab, *name_b_tab; - - name_a_tab = strchr(ecbdata->label_path[0], ' ') ? "\t" : ""; - name_b_tab = strchr(ecbdata->label_path[1], ' ') ? "\t" : ""; - - fprintf(o->file, "%s%s--- %s%s%s\n", - line_prefix, meta, ecbdata->label_path[0], reset, name_a_tab); - fprintf(o->file, "%s%s+++ %s%s%s\n", - line_prefix, meta, ecbdata->label_path[1], reset, name_b_tab); + emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_MINUS, + ecbdata->label_path[0], + strlen(ecbdata->label_path[0]), 0); + emit_diff_symbol(o, DIFF_SYMBOL_FILEPAIR_PLUS, + ecbdata->label_path[1], + strlen(ecbdata->label_path[1]), 0); ecbdata->label_path[0] = ecbdata->label_path[1] = NULL; } @@@ -2056,13 -1312,12 +2056,13 @@@ len = sane_truncate_line(ecbdata, line, len); find_lno(line, ecbdata); emit_hunk_header(ecbdata, line, len); - if (line[len-1] != '\n') - putc('\n', o->file); return; } if (ecbdata->diff_words) { + enum diff_symbol s = + ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN ? + DIFF_SYMBOL_WORDS_PORCELAIN : DIFF_SYMBOL_WORDS; if (line[0] == '-') { diff_words_append(line, len, &ecbdata->diff_words->minus); @@@ -2082,7 -1337,21 +2082,7 @@@ return; } diff_words_flush(ecbdata); - if (ecbdata->diff_words->type == DIFF_WORDS_PORCELAIN) { - emit_line(o, context, reset, line, len); - fputs("~\n", o->file); - } else { - /* - * Skip the prefix character, if any. With - * diff_suppress_blank_empty, there may be - * none. - */ - if (line[0] != '\n') { - line++; - len--; - } - emit_line(o, context, reset, line, len); - } + emit_diff_symbol(o, s, line, len, 0); return; } @@@ -2103,8 -1372,8 +2103,8 @@@ default: /* incomplete line at the end */ ecbdata->lno_in_preimage++; - emit_line(o, diff_get_color(ecbdata->color_diff, DIFF_CONTEXT), - reset, line, len); + emit_diff_symbol(o, DIFF_SYMBOL_CONTEXT_INCOMPLETE, + line, len, 0); break; } } @@@ -2249,14 -1518,20 +2249,14 @@@ static int scale_linear(int it, int wid return 1 + (it * (width - 1) / max_change); } -static void show_name(FILE *file, - const char *prefix, const char *name, int len) -{ - fprintf(file, " %s%-*s |", prefix, len, name); -} - -static void show_graph(FILE *file, char ch, int cnt, const char *set, const char *reset) +static void show_graph(struct strbuf *out, char ch, int cnt, + const char *set, const char *reset) { if (cnt <= 0) return; - fprintf(file, "%s", set); - while (cnt--) - putc(ch, file); - fprintf(file, "%s", reset); + strbuf_addstr(out, set); + strbuf_addchars(out, ch, cnt); + strbuf_addstr(out, reset); } static void fill_print_name(struct diffstat_file *file) @@@ -2280,16 -1555,14 +2280,16 @@@ file->print_name = pname; } -int print_stat_summary(FILE *fp, int files, int insertions, int deletions) +static void print_stat_summary_inserts_deletes(struct diff_options *options, + int files, int insertions, int deletions) { struct strbuf sb = STRBUF_INIT; - int ret; if (!files) { assert(insertions == 0 && deletions == 0); - return fprintf(fp, "%s\n", " 0 files changed"); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_SUMMARY_NO_FILES, + NULL, 0, 0); + return; } strbuf_addf(&sb, @@@ -2316,19 -1589,9 +2316,19 @@@ deletions); } strbuf_addch(&sb, '\n'); - ret = fputs(sb.buf, fp); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_SUMMARY_INSERTS_DELETES, + sb.buf, sb.len, 0); strbuf_release(&sb); - return ret; +} + +void print_stat_summary(FILE *fp, int files, + int insertions, int deletions) +{ + struct diff_options o; + memset(&o, 0, sizeof(o)); + o.file = fp; + + print_stat_summary_inserts_deletes(&o, files, insertions, deletions); } static void show_stats(struct diffstat_t *data, struct diff_options *options) @@@ -2338,13 -1601,13 +2338,13 @@@ int total_files = data->nr, count; int width, name_width, graph_width, number_width = 0, bin_width = 0; const char *reset, *add_c, *del_c; - const char *line_prefix = ""; int extra_shown = 0; + const char *line_prefix = diff_line_prefix(options); + struct strbuf out = STRBUF_INIT; if (data->nr == 0) return; - line_prefix = diff_line_prefix(options); count = options->stat_count ? options->stat_count : data->nr; reset = diff_get_color_opt(options, DIFF_RESET); @@@ -2498,32 -1761,26 +2498,32 @@@ } if (file->is_binary) { - fprintf(options->file, "%s", line_prefix); - show_name(options->file, prefix, name, len); - fprintf(options->file, " %*s", number_width, "Bin"); + strbuf_addf(&out, " %s%-*s |", prefix, len, name); + strbuf_addf(&out, " %*s", number_width, "Bin"); if (!added && !deleted) { - putc('\n', options->file); + strbuf_addch(&out, '\n'); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE, + out.buf, out.len, 0); + strbuf_reset(&out); continue; } - fprintf(options->file, " %s%"PRIuMAX"%s", + strbuf_addf(&out, " %s%"PRIuMAX"%s", del_c, deleted, reset); - fprintf(options->file, " -> "); - fprintf(options->file, "%s%"PRIuMAX"%s", + strbuf_addstr(&out, " -> "); + strbuf_addf(&out, "%s%"PRIuMAX"%s", add_c, added, reset); - fprintf(options->file, " bytes"); - fprintf(options->file, "\n"); + strbuf_addstr(&out, " bytes\n"); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE, + out.buf, out.len, 0); + strbuf_reset(&out); continue; } else if (file->is_unmerged) { - fprintf(options->file, "%s", line_prefix); - show_name(options->file, prefix, name, len); - fprintf(options->file, " Unmerged\n"); + strbuf_addf(&out, " %s%-*s |", prefix, len, name); + strbuf_addstr(&out, " Unmerged\n"); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE, + out.buf, out.len, 0); + strbuf_reset(&out); continue; } @@@ -2546,16 -1803,14 +2546,16 @@@ add = total - del; } } - fprintf(options->file, "%s", line_prefix); - show_name(options->file, prefix, name, len); - fprintf(options->file, " %*"PRIuMAX"%s", + strbuf_addf(&out, " %s%-*s |", prefix, len, name); + strbuf_addf(&out, " %*"PRIuMAX"%s", number_width, added + deleted, added + deleted ? " " : ""); - show_graph(options->file, '+', add, add_c, reset); - show_graph(options->file, '-', del, del_c, reset); - fprintf(options->file, "\n"); + show_graph(&out, '+', add, add_c, reset); + show_graph(&out, '-', del, del_c, reset); + strbuf_addch(&out, '\n'); + emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE, + out.buf, out.len, 0); + strbuf_reset(&out); } for (i = 0; i < data->nr; i++) { @@@ -2576,14 -1831,11 +2576,14 @@@ if (i < count) continue; if (!extra_shown) - fprintf(options->file, "%s ...\n", line_prefix); + emit_diff_symbol(options, + DIFF_SYMBOL_STATS_SUMMARY_ABBREV, + NULL, 0, 0); extra_shown = 1; } - fprintf(options->file, "%s", line_prefix); - print_stat_summary(options->file, total_files, adds, dels); + + print_stat_summary_inserts_deletes(options, total_files, adds, dels); + strbuf_release(&out); } static void show_shortstats(struct diffstat_t *data, struct diff_options *options) @@@ -2595,7 -1847,7 +2595,7 @@@ for (i = 0; i < data->nr; i++) { int added = data->files[i]->added; - int deleted= data->files[i]->deleted; + int deleted = data->files[i]->deleted; if (data->files[i]->is_unmerged || (!data->files[i]->is_interesting && (added + deleted == 0))) { @@@ -2605,7 -1857,8 +2605,7 @@@ dels += deleted; } } - fprintf(options->file, "%s", diff_line_prefix(options)); - print_stat_summary(options->file, total_files, adds, dels); + print_stat_summary_inserts_deletes(options, total_files, adds, dels); } static void show_numstat(struct diffstat_t *data, struct diff_options *options) @@@ -2969,8 -2222,8 +2969,8 @@@ static unsigned char *deflate_it(char * return deflated; } -static void emit_binary_diff_body(FILE *file, mmfile_t *one, mmfile_t *two, - const char *prefix) +static void emit_binary_diff_body(struct diff_options *o, + mmfile_t *one, mmfile_t *two) { void *cp; void *delta; @@@ -2999,18 -2252,13 +2999,18 @@@ } if (delta && delta_size < deflate_size) { - fprintf(file, "%sdelta %lu\n", prefix, orig_size); + char *s = xstrfmt("%lu", orig_size); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_DIFF_HEADER_DELTA, + s, strlen(s), 0); + free(s); free(deflated); data = delta; data_size = delta_size; - } - else { - fprintf(file, "%sliteral %lu\n", prefix, two->size); + } else { + char *s = xstrfmt("%lu", two->size); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_DIFF_HEADER_LITERAL, + s, strlen(s), 0); + free(s); free(delta); data = deflated; data_size = deflate_size; @@@ -3019,9 -2267,8 +3019,9 @@@ /* emit data encoded in base85 */ cp = data; while (data_size) { + int len; int bytes = (52 < data_size) ? 52 : data_size; - char line[70]; + char line[71]; data_size -= bytes; if (bytes <= 26) line[0] = bytes + 'A' - 1; @@@ -3029,24 -2276,20 +3029,24 @@@ line[0] = bytes - 26 + 'a' - 1; encode_85(line + 1, cp, bytes); cp = (char *) cp + bytes; - fprintf(file, "%s", prefix); - fputs(line, file); - fputc('\n', file); + + len = strlen(line); + line[len++] = '\n'; + line[len] = '\0'; + + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_DIFF_BODY, + line, len, 0); } - fprintf(file, "%s\n", prefix); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_DIFF_FOOTER, NULL, 0, 0); free(data); } -static void emit_binary_diff(FILE *file, mmfile_t *one, mmfile_t *two, - const char *prefix) +static void emit_binary_diff(struct diff_options *o, + mmfile_t *one, mmfile_t *two) { - fprintf(file, "%sGIT binary patch\n", prefix); - emit_binary_diff_body(file, one, two, prefix); - emit_binary_diff_body(file, two, one, prefix); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_DIFF_HEADER, NULL, 0, 0); + emit_binary_diff_body(o, one, two); + emit_binary_diff_body(o, two, one); } int diff_filespec_is_binary(struct diff_filespec *one) @@@ -3123,16 -2366,24 +3123,16 @@@ static void builtin_diff(const char *na if (o->submodule_format == DIFF_SUBMODULE_LOG && (!one->mode || S_ISGITLINK(one->mode)) && (!two->mode || S_ISGITLINK(two->mode))) { - const char *del = diff_get_color_opt(o, DIFF_FILE_OLD); - const char *add = diff_get_color_opt(o, DIFF_FILE_NEW); - show_submodule_summary(o->file, one->path ? one->path : two->path, - line_prefix, + show_submodule_summary(o, one->path ? one->path : two->path, &one->oid, &two->oid, - two->dirty_submodule, - meta, del, add, reset); + two->dirty_submodule); return; } else if (o->submodule_format == DIFF_SUBMODULE_INLINE_DIFF && (!one->mode || S_ISGITLINK(one->mode)) && (!two->mode || S_ISGITLINK(two->mode))) { - const char *del = diff_get_color_opt(o, DIFF_FILE_OLD); - const char *add = diff_get_color_opt(o, DIFF_FILE_NEW); - show_submodule_inline_diff(o->file, one->path ? one->path : two->path, - line_prefix, + show_submodule_inline_diff(o, one->path ? one->path : two->path, &one->oid, &two->oid, - two->dirty_submodule, - meta, del, add, reset, o); + two->dirty_submodule); return; } @@@ -3181,8 -2432,7 +3181,8 @@@ if (complete_rewrite && (textconv_one || !diff_filespec_is_binary(one)) && (textconv_two || !diff_filespec_is_binary(two))) { - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + header.buf, header.len, 0); strbuf_reset(&header); emit_rewrite_diff(name_a, name_b, one, two, textconv_one, textconv_two, o); @@@ -3192,31 -2442,23 +3192,31 @@@ } if (o->irreversible_delete && lbl[1][0] == '/') { - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, header.buf, + header.len, 0); strbuf_reset(&header); goto free_ab_and_return; } else if (!DIFF_OPT_TST(o, TEXT) && ( (!textconv_one && diff_filespec_is_binary(one)) || (!textconv_two && diff_filespec_is_binary(two)) )) { + struct strbuf sb = STRBUF_INIT; if (!one->data && !two->data && S_ISREG(one->mode) && S_ISREG(two->mode) && !DIFF_OPT_TST(o, BINARY)) { if (!oidcmp(&one->oid, &two->oid)) { if (must_show_header) - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + header.buf, header.len, + 0); goto free_ab_and_return; } - fprintf(o->file, "%s", header.buf); - fprintf(o->file, "%sBinary files %s and %s differ\n", - line_prefix, lbl[0], lbl[1]); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + header.buf, header.len, 0); + strbuf_addf(&sb, "%sBinary files %s and %s differ\n", + diff_line_prefix(o), lbl[0], lbl[1]); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_FILES, + sb.buf, sb.len, 0); + strbuf_release(&sb); goto free_ab_and_return; } if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) @@@ -3225,21 -2467,16 +3225,21 @@@ if (mf1.size == mf2.size && !memcmp(mf1.ptr, mf2.ptr, mf1.size)) { if (must_show_header) - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + header.buf, header.len, 0); goto free_ab_and_return; } - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, header.buf, header.len, 0); strbuf_reset(&header); if (DIFF_OPT_TST(o, BINARY)) - emit_binary_diff(o->file, &mf1, &mf2, line_prefix); - else - fprintf(o->file, "%sBinary files %s and %s differ\n", - line_prefix, lbl[0], lbl[1]); + emit_binary_diff(o, &mf1, &mf2); + else { + strbuf_addf(&sb, "%sBinary files %s and %s differ\n", + diff_line_prefix(o), lbl[0], lbl[1]); + emit_diff_symbol(o, DIFF_SYMBOL_BINARY_FILES, + sb.buf, sb.len, 0); + strbuf_release(&sb); + } o->found_changes = 1; } else { /* Crazy xdl interfaces.. */ @@@ -3251,8 -2488,7 +3251,8 @@@ const struct userdiff_funcname *pe; if (must_show_header) { - fprintf(o->file, "%s", header.buf); + emit_diff_symbol(o, DIFF_SYMBOL_HEADER, + header.buf, header.len, 0); strbuf_reset(&header); } @@@ -3721,6 -2957,7 +3721,6 @@@ static void prep_temp_blob(const char * const struct object_id *oid, int mode) { - int fd; struct strbuf buf = STRBUF_INIT; struct strbuf template = STRBUF_INIT; char *path_dup = xstrdup(path); @@@ -3730,18 -2967,18 +3730,18 @@@ strbuf_addstr(&template, "XXXXXX_"); strbuf_addstr(&template, base); - fd = mks_tempfile_ts(&temp->tempfile, template.buf, strlen(base) + 1); - if (fd < 0) + temp->tempfile = mks_tempfile_ts(template.buf, strlen(base) + 1); + if (!temp->tempfile) die_errno("unable to create temp-file"); if (convert_to_working_tree(path, (const char *)blob, (size_t)size, &buf)) { blob = buf.buf; size = buf.len; } - if (write_in_full(temp->tempfile->fd, blob, size) != size || - if (write_in_full(fd, blob, size) < 0) ++ if (write_in_full(temp->tempfile->fd, blob, size) < 0 || + close_tempfile_gently(temp->tempfile)) die_errno("unable to write temp-file"); - close_tempfile(&temp->tempfile); - temp->name = get_tempfile_path(&temp->tempfile); + temp->name = get_tempfile_path(temp->tempfile); oid_to_hex_r(temp->hex, oid); xsnprintf(temp->mode, sizeof(temp->mode), "%06o", mode); strbuf_release(&buf); @@@ -4009,7 -3246,7 +4009,7 @@@ static void diff_fill_oid_info(struct d } if (lstat(one->path, &st) < 0) die_errno("stat '%s'", one->path); - if (index_path(one->oid.hash, one->path, &st, 0)) + if (index_path(&one->oid, one->path, &st, 0)) die("cannot hash %s", one->path); } } @@@ -4042,8 -3279,8 +4042,8 @@@ static void run_diff(struct diff_filepa const char *other; const char *attr_path; - name = p->one->path; - other = (strcmp(name, p->two->path) ? p->two->path : NULL); + name = one->path; + other = (strcmp(name, two->path) ? two->path : NULL); attr_path = name; if (o->prefix_length) strip_prefix(o->prefix_length, &name, &other); @@@ -4166,8 -3403,6 +4166,8 @@@ void diff_setup(struct diff_options *op options->a_prefix = "a/"; options->b_prefix = "b/"; } + + options->color_moved = diff_color_moved_default; } void diff_setup_done(struct diff_options *options) @@@ -4277,9 -3512,6 +4277,9 @@@ if (DIFF_OPT_TST(options, FOLLOW_RENAMES) && options->pathspec.nr != 1) die(_("--follow requires exactly one pathspec")); + + if (!options->use_color || external_diff()) + options->color_moved = 0; } static int opt_arg(const char *arg, int arg_short, const char *arg_long, int *val) @@@ -4704,19 -3936,7 +4704,19 @@@ int diff_opt_parse(struct diff_options } else if (!strcmp(arg, "--no-color")) options->use_color = 0; - else if (!strcmp(arg, "--color-words")) { + else if (!strcmp(arg, "--color-moved")) { + if (diff_color_moved_default) + options->color_moved = diff_color_moved_default; + if (options->color_moved == COLOR_MOVED_NO) + options->color_moved = COLOR_MOVED_DEFAULT; + } else if (!strcmp(arg, "--no-color-moved")) + options->color_moved = COLOR_MOVED_NO; + else if (skip_prefix(arg, "--color-moved=", &arg)) { + int cm = parse_color_moved(arg); + if (cm < 0) + die("bad --color-moved argument: %s", arg); + options->color_moved = cm; + } else if (!strcmp(arg, "--color-words")) { options->use_color = 1; options->word_diff = DIFF_WORDS_COLOR; } @@@ -5246,78 -4466,67 +5246,78 @@@ static void flush_one_pair(struct diff_ } } -static void show_file_mode_name(FILE *file, const char *newdelete, struct diff_filespec *fs) +static void show_file_mode_name(struct diff_options *opt, const char *newdelete, struct diff_filespec *fs) { + struct strbuf sb = STRBUF_INIT; if (fs->mode) - fprintf(file, " %s mode %06o ", newdelete, fs->mode); + strbuf_addf(&sb, " %s mode %06o ", newdelete, fs->mode); else - fprintf(file, " %s ", newdelete); - write_name_quoted(fs->path, file, '\n'); -} + strbuf_addf(&sb, " %s ", newdelete); + quote_c_style(fs->path, &sb, NULL, 0); + strbuf_addch(&sb, '\n'); + emit_diff_symbol(opt, DIFF_SYMBOL_SUMMARY, + sb.buf, sb.len, 0); + strbuf_release(&sb); +} -static void show_mode_change(FILE *file, struct diff_filepair *p, int show_name, - const char *line_prefix) +static void show_mode_change(struct diff_options *opt, struct diff_filepair *p, + int show_name) { if (p->one->mode && p->two->mode && p->one->mode != p->two->mode) { - fprintf(file, "%s mode change %06o => %06o%c", line_prefix, p->one->mode, - p->two->mode, show_name ? ' ' : '\n'); + struct strbuf sb = STRBUF_INIT; + strbuf_addf(&sb, " mode change %06o => %06o", + p->one->mode, p->two->mode); if (show_name) { - write_name_quoted(p->two->path, file, '\n'); + strbuf_addch(&sb, ' '); + quote_c_style(p->two->path, &sb, NULL, 0); } + emit_diff_symbol(opt, DIFF_SYMBOL_SUMMARY, + sb.buf, sb.len, 0); + strbuf_release(&sb); } } -static void show_rename_copy(FILE *file, const char *renamecopy, struct diff_filepair *p, - const char *line_prefix) +static void show_rename_copy(struct diff_options *opt, const char *renamecopy, + struct diff_filepair *p) { + struct strbuf sb = STRBUF_INIT; char *names = pprint_rename(p->one->path, p->two->path); - - fprintf(file, " %s %s (%d%%)\n", renamecopy, names, similarity_index(p)); + strbuf_addf(&sb, " %s %s (%d%%)\n", + renamecopy, names, similarity_index(p)); free(names); - show_mode_change(file, p, 0, line_prefix); + emit_diff_symbol(opt, DIFF_SYMBOL_SUMMARY, + sb.buf, sb.len, 0); + show_mode_change(opt, p, 0); + strbuf_release(&sb); } static void diff_summary(struct diff_options *opt, struct diff_filepair *p) { - FILE *file = opt->file; - const char *line_prefix = diff_line_prefix(opt); - switch(p->status) { case DIFF_STATUS_DELETED: - fputs(line_prefix, file); - show_file_mode_name(file, "delete", p->one); + show_file_mode_name(opt, "delete", p->one); break; case DIFF_STATUS_ADDED: - fputs(line_prefix, file); - show_file_mode_name(file, "create", p->two); + show_file_mode_name(opt, "create", p->two); break; case DIFF_STATUS_COPIED: - fputs(line_prefix, file); - show_rename_copy(file, "copy", p, line_prefix); + show_rename_copy(opt, "copy", p); break; case DIFF_STATUS_RENAMED: - fputs(line_prefix, file); - show_rename_copy(file, "rename", p, line_prefix); + show_rename_copy(opt, "rename", p); break; default: if (p->score) { - fprintf(file, "%s rewrite ", line_prefix); - write_name_quoted(p->two->path, file, ' '); - fprintf(file, "(%d%%)\n", similarity_index(p)); + struct strbuf sb = STRBUF_INIT; + strbuf_addstr(&sb, " rewrite "); + quote_c_style(p->two->path, &sb, NULL, 0); + strbuf_addf(&sb, " (%d%%)\n", similarity_index(p)); + emit_diff_symbol(opt, DIFF_SYMBOL_SUMMARY, + sb.buf, sb.len, 0); + strbuf_release(&sb); } - show_mode_change(file, p, !p->score, line_prefix); + show_mode_change(opt, p, !p->score); break; } } @@@ -5522,51 -4731,6 +5522,51 @@@ void diff_warn_rename_limit(const char warning(_(rename_limit_advice), varname, needed); } +static void diff_flush_patch_all_file_pairs(struct diff_options *o) +{ + int i; + static struct emitted_diff_symbols esm = EMITTED_DIFF_SYMBOLS_INIT; + struct diff_queue_struct *q = &diff_queued_diff; + + if (WSEH_NEW & WS_RULE_MASK) + die("BUG: WS rules bit mask overlaps with diff symbol flags"); + + if (o->color_moved) + o->emitted_symbols = &esm; + + for (i = 0; i < q->nr; i++) { + struct diff_filepair *p = q->queue[i]; + if (check_pair_status(p)) + diff_flush_patch(p, o); + } + + if (o->emitted_symbols) { + if (o->color_moved) { + struct hashmap add_lines, del_lines; + + hashmap_init(&del_lines, + (hashmap_cmp_fn)moved_entry_cmp, o, 0); + hashmap_init(&add_lines, + (hashmap_cmp_fn)moved_entry_cmp, o, 0); + + add_lines_to_move_detection(o, &add_lines, &del_lines); + mark_color_as_moved(o, &add_lines, &del_lines); + if (o->color_moved == COLOR_MOVED_ZEBRA_DIM) + dim_moved_lines(o); + + hashmap_free(&add_lines, 0); + hashmap_free(&del_lines, 0); + } + + for (i = 0; i < esm.nr; i++) + emit_diff_symbol_from_struct(o, &esm.buf[i]); + + for (i = 0; i < esm.nr; i++) + free((void *)esm.buf[i].line); + } + esm.nr = 0; +} + void diff_flush(struct diff_options *options) { struct diff_queue_struct *q = &diff_queued_diff; @@@ -5639,7 -4803,6 +5639,7 @@@ fclose(options->file); options->file = xfopen("/dev/null", "w"); options->close_file = 1; + options->color_moved = 0; for (i = 0; i < q->nr; i++) { struct diff_filepair *p = q->queue[i]; if (check_pair_status(p)) @@@ -5651,14 -4814,20 +5651,14 @@@ if (output_format & DIFF_FORMAT_PATCH) { if (separator) { - fprintf(options->file, "%s%c", - diff_line_prefix(options), - options->line_termination); - if (options->stat_sep) { + emit_diff_symbol(options, DIFF_SYMBOL_SEPARATOR, NULL, 0, 0); + if (options->stat_sep) /* attach patch instead of inline */ - fputs(options->stat_sep, options->file); - } + emit_diff_symbol(options, DIFF_SYMBOL_STAT_SEP, + NULL, 0, 0); } - for (i = 0; i < q->nr; i++) { - struct diff_filepair *p = q->queue[i]; - if (check_pair_status(p)) - diff_flush_patch(p, options); - } + diff_flush_patch_all_file_pairs(options); } if (output_format & DIFF_FORMAT_CALLBACK) diff --combined entry.c index cb291aa88b,3c1818f1d4..1c7e3c11d5 --- a/entry.c +++ b/entry.c @@@ -3,7 -3,6 +3,7 @@@ #include "dir.h" #include "streaming.h" #include "submodule.h" +#include "progress.h" static void create_directories(const char *path, int path_len, const struct checkout *state) @@@ -162,22 -161,16 +162,22 @@@ static int remove_available_paths(struc int finish_delayed_checkout(struct checkout *state) { int errs = 0; + unsigned delayed_object_count; + off_t filtered_bytes = 0; struct string_list_item *filter, *path; + struct progress *progress; struct delayed_checkout *dco = state->delayed_checkout; if (!state->delayed_checkout) return errs; dco->state = CE_RETRY; + delayed_object_count = dco->paths.nr; + progress = start_delayed_progress(_("Filtering content"), delayed_object_count); while (dco->filters.nr > 0) { for_each_string_list_item(filter, &dco->filters) { struct string_list available_paths = STRING_LIST_INIT_NODUP; + display_progress(progress, delayed_object_count - dco->paths.nr); if (!async_query_available_blobs(filter->string, &available_paths)) { /* Filter reported an error */ @@@ -223,17 -216,11 +223,17 @@@ } ce = index_file_exists(state->istate, path->string, strlen(path->string), 0); - errs |= (ce ? checkout_entry(ce, state, NULL) : 1); + if (ce) { + errs |= checkout_entry(ce, state, NULL); + filtered_bytes += ce->ce_stat_data.sd_size; + display_throughput(progress, filtered_bytes); + } else + errs = 1; } } string_list_remove_empty_items(&dco->filters, 0); } + stop_progress(&progress); string_list_clear(&dco->filters, 0); /* At this point we should not have any delayed paths anymore. */ @@@ -257,7 -244,8 +257,8 @@@ static int write_entry(struct cache_ent char *new; struct strbuf buf = STRBUF_INIT; unsigned long size; - size_t wrote, newsize = 0; + ssize_t wrote; + size_t newsize = 0; struct stat st; const struct submodule *sub; @@@ -332,7 -320,7 +333,7 @@@ fstat_done = fstat_output(fd, state, &st); close(fd); free(new); - if (wrote != size) + if (wrote < 0) return error("unable to write file %s", path); break; case S_IFGITLINK: diff --combined fast-import.c index 49516d60e6,395524039b..35bf671f12 --- a/fast-import.c +++ b/fast-import.c @@@ -167,7 -167,6 +167,7 @@@ Format of STDIN stream #include "quote.h" #include "dir.h" #include "run-command.h" +#include "packfile.h" #define PACK_ID_BITS 16 #define MAX_PACK_ID ((1< 0) { - long ret = write_in_full(fd, buf, size); + ssize_t ret = write_in_full(fd, buf, size); if (ret < 0) { /* Ignore epipe */ if (errno == EPIPE) @@@ -624,7 -624,7 +624,7 @@@ int notes_merge(struct notes_merge_opti if (!oidcmp(&remote->object.oid, base_oid)) { /* Already merged; result == local commit */ if (o->verbosity >= 2) - printf("Already up-to-date!\n"); + printf("Already up to date!\n"); oidcpy(result_oid, &local->object.oid); goto found_result; } @@@ -709,7 -709,7 +709,7 @@@ int notes_merge_commit(struct notes_mer /* write file as blob, and add to partial_tree */ if (stat(path.buf, &st)) die_errno("Failed to stat '%s'", path.buf); - if (index_path(blob_oid.hash, path.buf, &st, HASH_WRITE_OBJECT)) + if (index_path(&blob_oid, path.buf, &st, HASH_WRITE_OBJECT)) die("Failed to write blob object from '%s'", path.buf); if (add_note(partial_tree, &obj_oid, &blob_oid, NULL)) die("Failed to add resolved note '%s' to notes tree", diff --combined pkt-line.c index f364944b93,4823d3bb9d..647bbd3bce --- a/pkt-line.c +++ b/pkt-line.c @@@ -94,9 -94,9 +94,9 @@@ void packet_flush(int fd int packet_flush_gently(int fd) { packet_trace("0000", 4, 1); - if (write_in_full(fd, "0000", 4) == 4) - return 0; - return error("flush packet write failed"); + if (write_in_full(fd, "0000", 4) < 0) + return error("flush packet write failed"); + return 0; } void packet_buf_flush(struct strbuf *buf) @@@ -136,20 -136,18 +136,19 @@@ static void format_packet(struct strbu static int packet_write_fmt_1(int fd, int gently, const char *fmt, va_list args) { - struct strbuf buf = STRBUF_INIT; + static struct strbuf buf = STRBUF_INIT; - ssize_t count; + strbuf_reset(&buf); format_packet(&buf, fmt, args); - count = write_in_full(fd, buf.buf, buf.len); - if (count == buf.len) - return 0; - - if (!gently) { - check_pipe(errno); - die_errno("packet write with format failed"); + if (write_in_full(fd, buf.buf, buf.len) < 0) { + if (!gently) { + check_pipe(errno); + die_errno("packet write with format failed"); + } + return error("packet write with format failed"); } - return error("packet write with format failed"); + + return 0; } void packet_write_fmt(int fd, const char *fmt, ...) @@@ -184,9 -182,9 +183,9 @@@ static int packet_write_gently(const in packet_size = size + 4; set_packet_header(packet_write_buffer, packet_size); memcpy(packet_write_buffer + 4, buf, size); - if (write_in_full(fd_out, packet_write_buffer, packet_size) == packet_size) - return 0; - return error("packet write failed"); + if (write_in_full(fd_out, packet_write_buffer, packet_size) < 0) + return error("packet write failed"); + return 0; } void packet_buf_write(struct strbuf *buf, const char *fmt, ...) diff --combined read-cache.c index 7d00265c49,5e6d24d444..cdcd11c71e --- a/read-cache.c +++ b/read-cache.c @@@ -160,9 -160,9 +160,9 @@@ static int ce_compare_data(const struc int fd = git_open_cloexec(ce->name, O_RDONLY); if (fd >= 0) { - unsigned char sha1[20]; - if (!index_fd(sha1, fd, st, OBJ_BLOB, ce->name, 0)) - match = hashcmp(sha1, ce->oid.hash); + struct object_id oid; + if (!index_fd(&oid, fd, st, OBJ_BLOB, ce->name, 0)) + match = oidcmp(&oid, &ce->oid); /* index_fd() closed the file descriptor already */ } return match; @@@ -689,7 -689,7 +689,7 @@@ int add_to_index(struct index_state *is return 0; } if (!intent_only) { - if (index_path(ce->oid.hash, path, st, HASH_WRITE_OBJECT)) { + if (index_path(&ce->oid, path, st, HASH_WRITE_OBJECT)) { free(ce); return error("unable to index file %s", path); } @@@ -1499,7 -1499,6 +1499,7 @@@ struct ondisk_cache_entry_extended }; /* These are only used for v3 or lower */ +#define align_padding_size(size, len) ((size + (len) + 8) & ~7) - (size + len) #define align_flex_name(STRUCT,len) ((offsetof(struct STRUCT,name) + (len) + 8) & ~7) #define ondisk_cache_entry_size(len) align_flex_name(ondisk_cache_entry,len) #define ondisk_cache_entry_extended_size(len) align_flex_name(ondisk_cache_entry_extended,len) @@@ -1922,7 -1921,7 +1922,7 @@@ static int ce_write_flush(git_SHA_CTX * unsigned int buffered = write_buffer_len; if (buffered) { git_SHA1_Update(context, write_buffer, buffered); - if (write_in_full(fd, write_buffer, buffered) != buffered) + if (write_in_full(fd, write_buffer, buffered) < 0) return -1; write_buffer_len = 0; } @@@ -1971,7 -1970,7 +1971,7 @@@ static int ce_flush(git_SHA_CTX *contex /* Flush first if not enough space for SHA1 signature */ if (left + 20 > WRITE_BUFFER_SIZE) { - if (write_in_full(fd, write_buffer, left) != left) + if (write_in_full(fd, write_buffer, left) < 0) return -1; left = 0; } @@@ -1980,7 -1979,7 +1980,7 @@@ git_SHA1_Final(write_buffer + left, context); hashcpy(sha1, write_buffer + left); left += 20; - return (write_in_full(fd, write_buffer, left) != left) ? -1 : 0; + return (write_in_full(fd, write_buffer, left) < 0) ? -1 : 0; } static void ce_smudge_racily_clean_entry(struct cache_entry *ce) @@@ -2033,7 -2032,7 +2033,7 @@@ } /* Copy miscellaneous fields but not the name */ -static char *copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk, +static void copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk, struct cache_entry *ce) { short flags; @@@ -2057,35 -2056,32 +2057,35 @@@ struct ondisk_cache_entry_extended *ondisk2; ondisk2 = (struct ondisk_cache_entry_extended *)ondisk; ondisk2->flags2 = htons((ce->ce_flags & CE_EXTENDED_FLAGS) >> 16); - return ondisk2->name; - } - else { - return ondisk->name; } } static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce, - struct strbuf *previous_name) + struct strbuf *previous_name, struct ondisk_cache_entry *ondisk) { int size; - struct ondisk_cache_entry *ondisk; int saved_namelen = saved_namelen; /* compiler workaround */ - char *name; int result; + static unsigned char padding[8] = { 0x00 }; if (ce->ce_flags & CE_STRIP_NAME) { saved_namelen = ce_namelen(ce); ce->ce_namelen = 0; } + if (ce->ce_flags & CE_EXTENDED) + size = offsetof(struct ondisk_cache_entry_extended, name); + else + size = offsetof(struct ondisk_cache_entry, name); + if (!previous_name) { - size = ondisk_ce_size(ce); - ondisk = xcalloc(1, size); - name = copy_cache_entry_to_ondisk(ondisk, ce); - memcpy(name, ce->name, ce_namelen(ce)); + int len = ce_namelen(ce); + copy_cache_entry_to_ondisk(ondisk, ce); + result = ce_write(c, fd, ondisk, size); + if (!result) + result = ce_write(c, fd, ce->name, len); + if (!result) + result = ce_write(c, fd, padding, align_padding_size(size, len)); } else { int common, to_remove, prefix_size; unsigned char to_remove_vi[16]; @@@ -2098,14 -2094,16 +2098,14 @@@ to_remove = previous_name->len - common; prefix_size = encode_varint(to_remove, to_remove_vi); - if (ce->ce_flags & CE_EXTENDED) - size = offsetof(struct ondisk_cache_entry_extended, name); - else - size = offsetof(struct ondisk_cache_entry, name); - size += prefix_size + (ce_namelen(ce) - common + 1); - - ondisk = xcalloc(1, size); - name = copy_cache_entry_to_ondisk(ondisk, ce); - memcpy(name, to_remove_vi, prefix_size); - memcpy(name + prefix_size, ce->name + common, ce_namelen(ce) - common); + copy_cache_entry_to_ondisk(ondisk, ce); + result = ce_write(c, fd, ondisk, size); + if (!result) + result = ce_write(c, fd, to_remove_vi, prefix_size); + if (!result) + result = ce_write(c, fd, ce->name + common, ce_namelen(ce) - common); + if (!result) + result = ce_write(c, fd, padding, 1); strbuf_splice(previous_name, common, to_remove, ce->name + common, ce_namelen(ce) - common); @@@ -2115,6 -2113,8 +2115,6 @@@ ce->ce_flags &= ~CE_STRIP_NAME; } - result = ce_write(c, fd, ondisk, size); - free(ondisk); return result; } @@@ -2192,11 -2192,10 +2192,11 @@@ static int do_write_index(struct index_ int newfd = tempfile->fd; git_SHA_CTX c; struct cache_header hdr; - int i, err, removed, extended, hdr_version; + int i, err = 0, removed, extended, hdr_version; struct cache_entry **cache = istate->cache; int entries = istate->cache_nr; struct stat st; + struct ondisk_cache_entry_extended ondisk; struct strbuf previous_name_buf = STRBUF_INIT, *previous_name; int drop_cache_tree = 0; @@@ -2233,7 -2232,6 +2233,7 @@@ return -1; previous_name = (hdr_version == 4) ? &previous_name_buf : NULL; + for (i = 0; i < entries; i++) { struct cache_entry *ce = cache[i]; if (ce->ce_flags & CE_REMOVE) @@@ -2249,21 -2247,15 +2249,21 @@@ if (allow) warning(msg, ce->name); else - return error(msg, ce->name); + err = error(msg, ce->name); drop_cache_tree = 1; } - if (ce_write_entry(&c, newfd, ce, previous_name) < 0) - return -1; + if (ce_write_entry(&c, newfd, ce, previous_name, (struct ondisk_cache_entry *)&ondisk) < 0) + err = -1; + + if (err) + break; } strbuf_release(&previous_name_buf); + if (err) + return err; + /* Write extension data here */ if (!strip_extensions && istate->split_index) { struct strbuf sb = STRBUF_INIT; @@@ -2311,11 -2303,8 +2311,11 @@@ if (ce_flush(&c, newfd, istate->sha1)) return -1; - if (close_tempfile(tempfile)) - return error(_("could not close '%s'"), tempfile->filename.buf); + if (close_tempfile_gently(tempfile)) { + error(_("could not close '%s'"), tempfile->filename.buf); + delete_tempfile(&tempfile); + return -1; + } if (stat(tempfile->filename.buf, &st)) return -1; istate->timestamp.sec = (unsigned int)st.st_mtime; @@@ -2339,7 -2328,7 +2339,7 @@@ static int commit_locked_index(struct l static int do_write_locked_index(struct index_state *istate, struct lock_file *lock, unsigned flags) { - int ret = do_write_index(istate, &lock->tempfile, 0); + int ret = do_write_index(istate, lock->tempfile, 0); if (ret) return ret; assert((flags & (COMMIT_LOCK | CLOSE_LOCK)) != @@@ -2347,7 -2336,7 +2347,7 @@@ if (flags & COMMIT_LOCK) return commit_locked_index(lock); else if (flags & CLOSE_LOCK) - return close_lock_file(lock); + return close_lock_file_gently(lock); else return ret; } @@@ -2422,33 -2411,34 +2422,33 @@@ static int clean_shared_index_files(con return 0; } -static struct tempfile temporary_sharedindex; - static int write_shared_index(struct index_state *istate, struct lock_file *lock, unsigned flags) { + struct tempfile *temp; struct split_index *si = istate->split_index; - int fd, ret; + int ret; - fd = mks_tempfile(&temporary_sharedindex, git_path("sharedindex_XXXXXX")); - if (fd < 0) { + temp = mks_tempfile(git_path("sharedindex_XXXXXX")); + if (!temp) { hashclr(si->base_sha1); return do_write_locked_index(istate, lock, flags); } move_cache_to_base_index(istate); - ret = do_write_index(si->base, &temporary_sharedindex, 1); + ret = do_write_index(si->base, temp, 1); if (ret) { - delete_tempfile(&temporary_sharedindex); + delete_tempfile(&temp); return ret; } - ret = adjust_shared_perm(get_tempfile_path(&temporary_sharedindex)); + ret = adjust_shared_perm(get_tempfile_path(temp)); if (ret) { int save_errno = errno; - error("cannot fix permission bits on %s", get_tempfile_path(&temporary_sharedindex)); - delete_tempfile(&temporary_sharedindex); + error("cannot fix permission bits on %s", get_tempfile_path(temp)); + delete_tempfile(&temp); errno = save_errno; return ret; } - ret = rename_tempfile(&temporary_sharedindex, + ret = rename_tempfile(&temp, git_path("sharedindex.%s", sha1_to_hex(si->base->sha1))); if (!ret) { hashcpy(si->base_sha1, si->base->sha1); diff --combined refs.c index c30f4c36be,a5abca04b7..e8b67ddce8 --- a/refs.c +++ b/refs.c @@@ -174,24 -174,6 +174,24 @@@ int refname_is_safe(const char *refname return 1; } +/* + * Return true if refname, which has the specified oid and flags, can + * be resolved to an object in the database. If the referred-to object + * does not exist, emit a warning and return false. + */ +int ref_resolves_to_object(const char *refname, + const struct object_id *oid, + unsigned int flags) +{ + if (flags & REF_ISBROKEN) + return 0; + if (!has_sha1_file(oid->hash)) { + error("%s does not point to a valid object!", refname); + return 0; + } + return 1; +} + char *refs_resolve_refdup(struct ref_store *refs, const char *refname, int resolve_flags, unsigned char *sha1, int *flags) @@@ -336,6 -318,12 +336,6 @@@ int for_each_tag_ref(each_ref_fn fn, vo return refs_for_each_tag_ref(get_main_ref_store(), fn, cb_data); } -int for_each_tag_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data) -{ - return refs_for_each_tag_ref(get_submodule_ref_store(submodule), - fn, cb_data); -} - int refs_for_each_branch_ref(struct ref_store *refs, each_ref_fn fn, void *cb_data) { return refs_for_each_ref_in(refs, "refs/heads/", fn, cb_data); @@@ -346,6 -334,12 +346,6 @@@ int for_each_branch_ref(each_ref_fn fn return refs_for_each_branch_ref(get_main_ref_store(), fn, cb_data); } -int for_each_branch_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data) -{ - return refs_for_each_branch_ref(get_submodule_ref_store(submodule), - fn, cb_data); -} - int refs_for_each_remote_ref(struct ref_store *refs, each_ref_fn fn, void *cb_data) { return refs_for_each_ref_in(refs, "refs/remotes/", fn, cb_data); @@@ -356,6 -350,12 +356,6 @@@ int for_each_remote_ref(each_ref_fn fn return refs_for_each_remote_ref(get_main_ref_store(), fn, cb_data); } -int for_each_remote_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data) -{ - return refs_for_each_remote_ref(get_submodule_ref_store(submodule), - fn, cb_data); -} - int head_ref_namespaced(each_ref_fn fn, void *cb_data) { struct strbuf buf = STRBUF_INIT; @@@ -561,21 -561,6 +561,21 @@@ enum ref_type ref_type(const char *refn return REF_TYPE_NORMAL; } +long get_files_ref_lock_timeout_ms(void) +{ + static int configured = 0; + + /* The default timeout is 100 ms: */ + static int timeout_ms = 100; + + if (!configured) { + git_config_get_int("core.filesreflocktimeout", &timeout_ms); + configured = 1; + } + + return timeout_ms; +} + static int write_pseudoref(const char *pseudoref, const unsigned char *sha1, const unsigned char *old_sha1, struct strbuf *err) { @@@ -588,13 -573,11 +588,13 @@@ strbuf_addf(&buf, "%s\n", sha1_to_hex(sha1)); filename = git_path("%s", pseudoref); - fd = hold_lock_file_for_update(&lock, filename, LOCK_DIE_ON_ERROR); + fd = hold_lock_file_for_update_timeout(&lock, filename, + LOCK_DIE_ON_ERROR, + get_files_ref_lock_timeout_ms()); if (fd < 0) { strbuf_addf(err, "could not open '%s' for writing: %s", filename, strerror(errno)); - return -1; + goto done; } if (old_sha1) { @@@ -609,7 -592,7 +609,7 @@@ } } - if (write_in_full(fd, buf.buf, buf.len) != buf.len) { + if (write_in_full(fd, buf.buf, buf.len) < 0) { strbuf_addf(err, "could not write to '%s'", filename); rollback_lock_file(&lock); goto done; @@@ -633,9 -616,8 +633,9 @@@ static int delete_pseudoref(const char int fd; unsigned char actual_old_sha1[20]; - fd = hold_lock_file_for_update(&lock, filename, - LOCK_DIE_ON_ERROR); + fd = hold_lock_file_for_update_timeout( + &lock, filename, LOCK_DIE_ON_ERROR, + get_files_ref_lock_timeout_ms()); if (fd < 0) die_errno(_("Could not open '%s' for writing"), filename); if (read_ref(pseudoref, actual_old_sha1)) @@@ -836,7 -818,7 +836,7 @@@ int read_ref_at(const char *refname, un for_each_reflog_ent_reverse(refname, read_ref_at_ent, &cb); if (!cb.reccnt) { - if (flags & GET_SHA1_QUIETLY) + if (flags & GET_OID_QUIETLY) exit(128); else die("Log for %s is empty.", refname); @@@ -1248,13 -1230,19 +1248,13 @@@ int refs_rename_ref_available(struct re return ok; } -int head_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data) +int refs_head_ref(struct ref_store *refs, each_ref_fn fn, void *cb_data) { struct object_id oid; int flag; - if (submodule) { - if (resolve_gitlink_ref(submodule, "HEAD", oid.hash) == 0) - return fn("HEAD", &oid, 0, cb_data); - - return 0; - } - - if (!read_ref_full("HEAD", RESOLVE_REF_READING, oid.hash, &flag)) + if (!refs_read_ref_full(refs, "HEAD", RESOLVE_REF_READING, + oid.hash, &flag)) return fn("HEAD", &oid, flag, cb_data); return 0; @@@ -1262,7 -1250,7 +1262,7 @@@ int head_ref(each_ref_fn fn, void *cb_data) { - return head_ref_submodule(NULL, fn, cb_data); + return refs_head_ref(get_main_ref_store(), fn, cb_data); } struct ref_iterator *refs_ref_iterator_begin( @@@ -1320,6 -1308,11 +1320,6 @@@ int for_each_ref(each_ref_fn fn, void * return refs_for_each_ref(get_main_ref_store(), fn, cb_data); } -int for_each_ref_submodule(const char *submodule, each_ref_fn fn, void *cb_data) -{ - return refs_for_each_ref(get_submodule_ref_store(submodule), fn, cb_data); -} - int refs_for_each_ref_in(struct ref_store *refs, const char *prefix, each_ref_fn fn, void *cb_data) { @@@ -1341,15 -1334,23 +1341,15 @@@ int for_each_fullref_in(const char *pre prefix, fn, 0, flag, cb_data); } -int for_each_ref_in_submodule(const char *submodule, const char *prefix, - each_ref_fn fn, void *cb_data) -{ - return refs_for_each_ref_in(get_submodule_ref_store(submodule), - prefix, fn, cb_data); -} - -int for_each_fullref_in_submodule(const char *submodule, const char *prefix, - each_ref_fn fn, void *cb_data, - unsigned int broken) +int refs_for_each_fullref_in(struct ref_store *refs, const char *prefix, + each_ref_fn fn, void *cb_data, + unsigned int broken) { unsigned int flag = 0; if (broken) flag = DO_FOR_EACH_INCLUDE_BROKEN; - return do_for_each_ref(get_submodule_ref_store(submodule), - prefix, fn, 0, flag, cb_data); + return do_for_each_ref(refs, prefix, fn, 0, flag, cb_data); } int for_each_replace_ref(each_ref_fn fn, void *cb_data) @@@ -1484,10 -1485,25 +1484,10 @@@ const char *resolve_ref_unsafe(const ch int resolve_gitlink_ref(const char *submodule, const char *refname, unsigned char *sha1) { - size_t len = strlen(submodule); struct ref_store *refs; int flags; - while (len && submodule[len - 1] == '/') - len--; - - if (!len) - return -1; - - if (submodule[len]) { - /* We need to strip off one or more trailing slashes */ - char *stripped = xmemdupz(submodule, len); - - refs = get_submodule_ref_store(stripped); - free(stripped); - } else { - refs = get_submodule_ref_store(submodule); - } + refs = get_submodule_ref_store(submodule); if (!refs) return -1; @@@ -1602,32 -1618,31 +1602,32 @@@ struct ref_store *get_submodule_ref_sto { struct strbuf submodule_sb = STRBUF_INIT; struct ref_store *refs; - int ret; + char *to_free = NULL; + size_t len; - if (!submodule || !*submodule) { - /* - * FIXME: This case is ideally not allowed. But that - * can't happen until we clean up all the callers. - */ - return get_main_ref_store(); - } + if (!submodule) + return NULL; + + len = strlen(submodule); + while (len && is_dir_sep(submodule[len - 1])) + len--; + if (!len) + return NULL; + + if (submodule[len]) + /* We need to strip off one or more trailing slashes */ + submodule = to_free = xmemdupz(submodule, len); refs = lookup_ref_store_map(&submodule_ref_stores, submodule); if (refs) - return refs; + goto done; strbuf_addstr(&submodule_sb, submodule); - ret = is_nonbare_repository_dir(&submodule_sb); - strbuf_release(&submodule_sb); - if (!ret) - return NULL; + if (!is_nonbare_repository_dir(&submodule_sb)) + goto done; - ret = submodule_to_gitdir(&submodule_sb, submodule); - if (ret) { - strbuf_release(&submodule_sb); - return NULL; - } + if (submodule_to_gitdir(&submodule_sb, submodule)) + goto done; /* assume that add_submodule_odb() has been called */ refs = ref_store_init(submodule_sb.buf, @@@ -1635,10 -1650,7 +1635,10 @@@ register_ref_store_map(&submodule_ref_stores, "submodule", refs, submodule); +done: strbuf_release(&submodule_sb); + free(to_free); + return refs; } diff --combined refs/files-backend.c index 32663a999e,f21a954ce7..dac33628b3 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@@ -3,7 -3,6 +3,7 @@@ #include "../refs.h" #include "refs-internal.h" #include "ref-cache.h" +#include "packed-backend.h" #include "../iterator.h" #include "../dir-iterator.h" #include "../lockfile.h" @@@ -12,10 -11,43 +12,10 @@@ struct ref_lock { char *ref_name; - struct lock_file *lk; + struct lock_file lk; struct object_id old_oid; }; -/* - * Return true if refname, which has the specified oid and flags, can - * be resolved to an object in the database. If the referred-to object - * does not exist, emit a warning and return false. - */ -static int ref_resolves_to_object(const char *refname, - const struct object_id *oid, - unsigned int flags) -{ - if (flags & REF_ISBROKEN) - return 0; - if (!has_sha1_file(oid->hash)) { - error("%s does not point to a valid object!", refname); - return 0; - } - return 1; -} - -struct packed_ref_cache { - struct ref_cache *cache; - - /* - * Count of references to the data structure in this instance, - * including the pointer from files_ref_store::packed if any. - * The data will not be freed as long as the reference count - * is nonzero. - */ - unsigned int referrers; - - /* The metadata from when this packed-refs cache was read */ - struct stat_validity validity; -}; - /* * Future: need to be in "struct repository" * when doing a full libification. @@@ -26,12 -58,54 +26,12 @@@ struct files_ref_store char *gitdir; char *gitcommondir; - char *packed_refs_path; struct ref_cache *loose; - struct packed_ref_cache *packed; - /* - * Lock used for the "packed-refs" file. Note that this (and - * thus the enclosing `files_ref_store`) must not be freed. - */ - struct lock_file packed_refs_lock; + struct ref_store *packed_ref_store; }; -/* - * Increment the reference count of *packed_refs. - */ -static void acquire_packed_ref_cache(struct packed_ref_cache *packed_refs) -{ - packed_refs->referrers++; -} - -/* - * Decrease the reference count of *packed_refs. If it goes to zero, - * free *packed_refs and return true; otherwise return false. - */ -static int release_packed_ref_cache(struct packed_ref_cache *packed_refs) -{ - if (!--packed_refs->referrers) { - free_ref_cache(packed_refs->cache); - stat_validity_clear(&packed_refs->validity); - free(packed_refs); - return 1; - } else { - return 0; - } -} - -static void clear_packed_ref_cache(struct files_ref_store *refs) -{ - if (refs->packed) { - struct packed_ref_cache *packed_refs = refs->packed; - - if (is_lock_file_locked(&refs->packed_refs_lock)) - die("BUG: packed-ref cache cleared while locked"); - refs->packed = NULL; - release_packed_ref_cache(packed_refs); - } -} - static void clear_loose_ref_cache(struct files_ref_store *refs) { if (refs->loose) { @@@ -58,8 -132,7 +58,8 @@@ static struct ref_store *files_ref_stor get_common_dir_noenv(&sb, gitdir); refs->gitcommondir = strbuf_detach(&sb, NULL); strbuf_addf(&sb, "%s/packed-refs", refs->gitcommondir); - refs->packed_refs_path = strbuf_detach(&sb, NULL); + refs->packed_ref_store = packed_ref_store_create(sb.buf, flags); + strbuf_release(&sb); return ref_store; } @@@ -102,10 -175,169 +102,10 @@@ static struct files_ref_store *files_do return refs; } -/* The length of a peeled reference line in packed-refs, including EOL: */ -#define PEELED_LINE_LENGTH 42 - -/* - * The packed-refs header line that we write out. Perhaps other - * traits will be added later. The trailing space is required. - */ -static const char PACKED_REFS_HEADER[] = - "# pack-refs with: peeled fully-peeled \n"; - -/* - * Parse one line from a packed-refs file. Write the SHA1 to sha1. - * Return a pointer to the refname within the line (null-terminated), - * or NULL if there was a problem. - */ -static const char *parse_ref_line(struct strbuf *line, struct object_id *oid) -{ - const char *ref; - - if (parse_oid_hex(line->buf, oid, &ref) < 0) - return NULL; - if (!isspace(*ref++)) - return NULL; - - if (isspace(*ref)) - return NULL; - - if (line->buf[line->len - 1] != '\n') - return NULL; - line->buf[--line->len] = 0; - - return ref; -} - -/* - * Read from `packed_refs_file` into a newly-allocated - * `packed_ref_cache` and return it. The return value will already - * have its reference count incremented. - * - * A comment line of the form "# pack-refs with: " may contain zero or - * more traits. We interpret the traits as follows: - * - * No traits: - * - * Probably no references are peeled. But if the file contains a - * peeled value for a reference, we will use it. - * - * peeled: - * - * References under "refs/tags/", if they *can* be peeled, *are* - * peeled in this file. References outside of "refs/tags/" are - * probably not peeled even if they could have been, but if we find - * a peeled value for such a reference we will use it. - * - * fully-peeled: - * - * All references in the file that can be peeled are peeled. - * Inversely (and this is more important), any references in the - * file for which no peeled value is recorded is not peelable. This - * trait should typically be written alongside "peeled" for - * compatibility with older clients, but we do not require it - * (i.e., "peeled" is a no-op if "fully-peeled" is set). - */ -static struct packed_ref_cache *read_packed_refs(const char *packed_refs_file) -{ - FILE *f; - struct packed_ref_cache *packed_refs = xcalloc(1, sizeof(*packed_refs)); - struct ref_entry *last = NULL; - struct strbuf line = STRBUF_INIT; - enum { PEELED_NONE, PEELED_TAGS, PEELED_FULLY } peeled = PEELED_NONE; - struct ref_dir *dir; - - acquire_packed_ref_cache(packed_refs); - packed_refs->cache = create_ref_cache(NULL, NULL); - packed_refs->cache->root->flag &= ~REF_INCOMPLETE; - - f = fopen(packed_refs_file, "r"); - if (!f) { - if (errno == ENOENT) { - /* - * This is OK; it just means that no - * "packed-refs" file has been written yet, - * which is equivalent to it being empty. - */ - return packed_refs; - } else { - die_errno("couldn't read %s", packed_refs_file); - } - } - - stat_validity_update(&packed_refs->validity, fileno(f)); - - dir = get_ref_dir(packed_refs->cache->root); - while (strbuf_getwholeline(&line, f, '\n') != EOF) { - struct object_id oid; - const char *refname; - const char *traits; - - if (skip_prefix(line.buf, "# pack-refs with:", &traits)) { - if (strstr(traits, " fully-peeled ")) - peeled = PEELED_FULLY; - else if (strstr(traits, " peeled ")) - peeled = PEELED_TAGS; - /* perhaps other traits later as well */ - continue; - } - - refname = parse_ref_line(&line, &oid); - if (refname) { - int flag = REF_ISPACKED; - - if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) { - if (!refname_is_safe(refname)) - die("packed refname is dangerous: %s", refname); - oidclr(&oid); - flag |= REF_BAD_NAME | REF_ISBROKEN; - } - last = create_ref_entry(refname, &oid, flag); - if (peeled == PEELED_FULLY || - (peeled == PEELED_TAGS && starts_with(refname, "refs/tags/"))) - last->flag |= REF_KNOWS_PEELED; - add_ref_entry(dir, last); - continue; - } - if (last && - line.buf[0] == '^' && - line.len == PEELED_LINE_LENGTH && - line.buf[PEELED_LINE_LENGTH - 1] == '\n' && - !get_oid_hex(line.buf + 1, &oid)) { - oidcpy(&last->u.value.peeled, &oid); - /* - * Regardless of what the file header said, - * we definitely know the value of *this* - * reference: - */ - last->flag |= REF_KNOWS_PEELED; - } - } - - fclose(f); - strbuf_release(&line); - - return packed_refs; -} - -static const char *files_packed_refs_path(struct files_ref_store *refs) -{ - return refs->packed_refs_path; -} - static void files_reflog_path(struct files_ref_store *refs, struct strbuf *sb, const char *refname) { - if (!refname) { - /* - * FIXME: of course this is wrong in multi worktree - * setting. To be fixed real soon. - */ - strbuf_addf(sb, "%s/logs", refs->gitcommondir); - return; - } - switch (ref_type(refname)) { case REF_TYPE_PER_WORKTREE: case REF_TYPE_PSEUDOREF: @@@ -138,6 -370,70 +138,6 @@@ static void files_ref_path(struct files } } -/* - * Check that the packed refs cache (if any) still reflects the - * contents of the file. If not, clear the cache. - */ -static void validate_packed_ref_cache(struct files_ref_store *refs) -{ - if (refs->packed && - !stat_validity_check(&refs->packed->validity, - files_packed_refs_path(refs))) - clear_packed_ref_cache(refs); -} - -/* - * Get the packed_ref_cache for the specified files_ref_store, - * creating and populating it if it hasn't been read before or if the - * file has been changed (according to its `validity` field) since it - * was last read. On the other hand, if we hold the lock, then assume - * that the file hasn't been changed out from under us, so skip the - * extra `stat()` call in `stat_validity_check()`. - */ -static struct packed_ref_cache *get_packed_ref_cache(struct files_ref_store *refs) -{ - const char *packed_refs_file = files_packed_refs_path(refs); - - if (!is_lock_file_locked(&refs->packed_refs_lock)) - validate_packed_ref_cache(refs); - - if (!refs->packed) - refs->packed = read_packed_refs(packed_refs_file); - - return refs->packed; -} - -static struct ref_dir *get_packed_ref_dir(struct packed_ref_cache *packed_ref_cache) -{ - return get_ref_dir(packed_ref_cache->cache->root); -} - -static struct ref_dir *get_packed_refs(struct files_ref_store *refs) -{ - return get_packed_ref_dir(get_packed_ref_cache(refs)); -} - -/* - * Add a reference to the in-memory packed reference cache. This may - * only be called while the packed-refs file is locked (see - * lock_packed_refs()). To actually write the packed-refs file, call - * commit_packed_refs(). - */ -static void add_packed_ref(struct files_ref_store *refs, - const char *refname, const struct object_id *oid) -{ - struct packed_ref_cache *packed_ref_cache = get_packed_ref_cache(refs); - - if (!is_lock_file_locked(&refs->packed_refs_lock)) - die("BUG: packed refs not locked"); - - if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) - die("Reference has invalid format: '%s'", refname); - - add_ref_entry(get_packed_ref_dir(packed_ref_cache), - create_ref_entry(refname, oid, REF_ISPACKED)); -} - /* * Read the loose references from the namespace dirname into dir * (without recursing). dirname must end with '/'. dir must be the @@@ -260,6 -556,39 +260,6 @@@ static struct ref_cache *get_loose_ref_ return refs->loose; } -/* - * Return the ref_entry for the given refname from the packed - * references. If it does not exist, return NULL. - */ -static struct ref_entry *get_packed_ref(struct files_ref_store *refs, - const char *refname) -{ - return find_ref_entry(get_packed_refs(refs), refname); -} - -/* - * A loose ref file doesn't exist; check for a packed ref. - */ -static int resolve_packed_ref(struct files_ref_store *refs, - const char *refname, - unsigned char *sha1, unsigned int *flags) -{ - struct ref_entry *entry; - - /* - * The loose reference file does not exist; check for a packed - * reference. - */ - entry = get_packed_ref(refs, refname); - if (entry) { - hashcpy(sha1, entry->u.value.oid.hash); - *flags |= REF_ISPACKED; - return 0; - } - /* refname is not a packed reference. */ - return -1; -} - static int files_read_raw_ref(struct ref_store *ref_store, const char *refname, unsigned char *sha1, struct strbuf *referent, unsigned int *type) @@@ -303,8 -632,7 +303,8 @@@ stat_ref if (lstat(path, &st) < 0) { if (errno != ENOENT) goto out; - if (resolve_packed_ref(refs, refname, sha1, type)) { + if (refs_read_raw_ref(refs->packed_ref_store, refname, + sha1, referent, type)) { errno = ENOENT; goto out; } @@@ -343,8 -671,7 +343,8 @@@ * ref is supposed to be, there could still be a * packed ref: */ - if (resolve_packed_ref(refs, refname, sha1, type)) { + if (refs_read_raw_ref(refs->packed_ref_store, refname, + sha1, referent, type)) { errno = EISDIR; goto out; } @@@ -409,7 -736,9 +409,7 @@@ out static void unlock_ref(struct ref_lock *lock) { - /* Do not free lock->lk -- atexit() still looks at them */ - if (lock->lk) - rollback_lock_file(lock->lk); + rollback_lock_file(&lock->lk); free(lock->ref_name); free(lock); } @@@ -523,9 -852,10 +523,9 @@@ retry goto error_return; } - if (!lock->lk) - lock->lk = xcalloc(1, sizeof(struct lock_file)); - - if (hold_lock_file_for_update(lock->lk, ref_file.buf, LOCK_NO_DEREF) < 0) { + if (hold_lock_file_for_update_timeout( + &lock->lk, ref_file.buf, LOCK_NO_DEREF, + get_files_ref_lock_timeout_ms()) < 0) { if (errno == ENOENT && --attempts_remaining > 0) { /* * Maybe somebody just deleted one of the @@@ -620,11 -950,11 +620,11 @@@ /* * If the ref did not exist and we are creating it, - * make sure there is no existing ref that conflicts - * with refname: + * make sure there is no existing packed ref that + * conflicts with refname: */ if (refs_verify_refname_available( - &refs->base, refname, + refs->packed_ref_store, refname, extras, skip, err)) goto error_return; } @@@ -671,9 -1001,15 +671,9 @@@ static int files_peel_ref(struct ref_st * be expensive and (b) loose references anyway usually do not * have REF_KNOWS_PEELED. */ - if (flag & REF_ISPACKED) { - struct ref_entry *r = get_packed_ref(refs, refname); - if (r) { - if (peel_entry(r, 0)) - return -1; - hashcpy(sha1, r->u.value.peeled.hash); - return 0; - } - } + if (flag & REF_ISPACKED && + !refs_peel_ref(refs->packed_ref_store, refname, sha1)) + return 0; return peel_object(base, sha1); } @@@ -681,6 -1017,7 +681,6 @@@ struct files_ref_iterator { struct ref_iterator base; - struct packed_ref_cache *packed_ref_cache; struct ref_iterator *iter0; unsigned int flags; }; @@@ -733,6 -1070,7 +733,6 @@@ static int files_ref_iterator_abort(str if (iter->iter0) ok = ref_iterator_abort(iter->iter0); - release_packed_ref_cache(iter->packed_ref_cache); base_ref_iterator_free(ref_iterator); return ok; } @@@ -774,28 -1112,18 +774,28 @@@ static struct ref_iterator *files_ref_i * (If they've already been read, that's OK; we only need to * guarantee that they're read before the packed refs, not * *how much* before.) After that, we call - * get_packed_ref_cache(), which internally checks whether the - * packed-ref cache is up to date with what is on disk, and - * re-reads it if not. + * packed_ref_iterator_begin(), which internally checks + * whether the packed-ref cache is up to date with what is on + * disk, and re-reads it if not. */ loose_iter = cache_ref_iterator_begin(get_loose_ref_cache(refs), prefix, 1); - iter->packed_ref_cache = get_packed_ref_cache(refs); - acquire_packed_ref_cache(iter->packed_ref_cache); - packed_iter = cache_ref_iterator_begin(iter->packed_ref_cache->cache, - prefix, 0); + /* + * The packed-refs file might contain broken references, for + * example an old version of a reference that points at an + * object that has since been garbage-collected. This is OK as + * long as there is a corresponding loose reference that + * overrides it, and we don't want to emit an error message in + * this case. So ask the packed_ref_store for all of its + * references, and (if needed) do our own check for broken + * ones in files_ref_iterator_advance(), after we have merged + * the packed and loose references. + */ + packed_iter = refs_ref_iterator_begin( + refs->packed_ref_store, prefix, 0, + DO_FOR_EACH_INCLUDE_BROKEN); iter->iter0 = overlay_ref_iterator_begin(loose_iter, packed_iter); iter->flags = flags; @@@ -853,9 -1181,7 +853,9 @@@ static int create_reflock(const char *p { struct lock_file *lk = cb; - return hold_lock_file_for_update(lk, path, LOCK_NO_DEREF) < 0 ? -1 : 0; + return hold_lock_file_for_update_timeout( + lk, path, LOCK_NO_DEREF, + get_files_ref_lock_timeout_ms()) < 0 ? -1 : 0; } /* @@@ -929,15 -1255,17 +929,15 @@@ static struct ref_lock *lock_ref_sha1_b * our refname. */ if (is_null_oid(&lock->old_oid) && - refs_verify_refname_available(&refs->base, refname, + refs_verify_refname_available(refs->packed_ref_store, refname, extras, skip, err)) { last_errno = ENOTDIR; goto error_return; } - lock->lk = xcalloc(1, sizeof(struct lock_file)); - lock->ref_name = xstrdup(refname); - if (raceproof_create_file(ref_file.buf, create_reflock, lock->lk)) { + if (raceproof_create_file(ref_file.buf, create_reflock, &lock->lk)) { last_errno = errno; unable_to_lock_message(ref_file.buf, errno, err); goto error_return; @@@ -959,6 -1287,124 +959,6 @@@ return lock; } -/* - * Write an entry to the packed-refs file for the specified refname. - * If peeled is non-NULL, write it as the entry's peeled value. - */ -static void write_packed_entry(FILE *fh, const char *refname, - const unsigned char *sha1, - const unsigned char *peeled) -{ - fprintf_or_die(fh, "%s %s\n", sha1_to_hex(sha1), refname); - if (peeled) - fprintf_or_die(fh, "^%s\n", sha1_to_hex(peeled)); -} - -/* - * Lock the packed-refs file for writing. Flags is passed to - * hold_lock_file_for_update(). Return 0 on success. On errors, set - * errno appropriately and return a nonzero value. - */ -static int lock_packed_refs(struct files_ref_store *refs, int flags) -{ - static int timeout_configured = 0; - static int timeout_value = 1000; - struct packed_ref_cache *packed_ref_cache; - - files_assert_main_repository(refs, "lock_packed_refs"); - - if (!timeout_configured) { - git_config_get_int("core.packedrefstimeout", &timeout_value); - timeout_configured = 1; - } - - if (hold_lock_file_for_update_timeout( - &refs->packed_refs_lock, files_packed_refs_path(refs), - flags, timeout_value) < 0) - return -1; - - /* - * Now that we hold the `packed-refs` lock, make sure that our - * cache matches the current version of the file. Normally - * `get_packed_ref_cache()` does that for us, but that - * function assumes that when the file is locked, any existing - * cache is still valid. We've just locked the file, but it - * might have changed the moment *before* we locked it. - */ - validate_packed_ref_cache(refs); - - packed_ref_cache = get_packed_ref_cache(refs); - /* Increment the reference count to prevent it from being freed: */ - acquire_packed_ref_cache(packed_ref_cache); - return 0; -} - -/* - * Write the current version of the packed refs cache from memory to - * disk. The packed-refs file must already be locked for writing (see - * lock_packed_refs()). Return zero on success. On errors, set errno - * and return a nonzero value - */ -static int commit_packed_refs(struct files_ref_store *refs) -{ - struct packed_ref_cache *packed_ref_cache = - get_packed_ref_cache(refs); - int ok, error = 0; - int save_errno = 0; - FILE *out; - struct ref_iterator *iter; - - files_assert_main_repository(refs, "commit_packed_refs"); - - if (!is_lock_file_locked(&refs->packed_refs_lock)) - die("BUG: packed-refs not locked"); - - out = fdopen_lock_file(&refs->packed_refs_lock, "w"); - if (!out) - die_errno("unable to fdopen packed-refs descriptor"); - - fprintf_or_die(out, "%s", PACKED_REFS_HEADER); - - iter = cache_ref_iterator_begin(packed_ref_cache->cache, NULL, 0); - while ((ok = ref_iterator_advance(iter)) == ITER_OK) { - struct object_id peeled; - int peel_error = ref_iterator_peel(iter, &peeled); - - write_packed_entry(out, iter->refname, iter->oid->hash, - peel_error ? NULL : peeled.hash); - } - - if (ok != ITER_DONE) - die("error while iterating over references"); - - if (commit_lock_file(&refs->packed_refs_lock)) { - save_errno = errno; - error = -1; - } - release_packed_ref_cache(packed_ref_cache); - errno = save_errno; - return error; -} - -/* - * Rollback the lockfile for the packed-refs file, and discard the - * in-memory packed reference cache. (The packed-refs file will be - * read anew if it is needed again after this function is called.) - */ -static void rollback_packed_refs(struct files_ref_store *refs) -{ - struct packed_ref_cache *packed_ref_cache = - get_packed_ref_cache(refs); - - files_assert_main_repository(refs, "rollback_packed_refs"); - - if (!is_lock_file_locked(&refs->packed_refs_lock)) - die("BUG: packed-refs not locked"); - rollback_lock_file(&refs->packed_refs_lock); - release_packed_ref_cache(packed_ref_cache); - clear_packed_ref_cache(refs); -} - struct ref_to_prune { struct ref_to_prune *next; unsigned char sha1[20]; @@@ -1041,17 -1487,11 +1041,17 @@@ static void prune_ref(struct files_ref_ strbuf_release(&err); } -static void prune_refs(struct files_ref_store *refs, struct ref_to_prune *r) +/* + * Prune the loose versions of the references in the linked list + * `*refs_to_prune`, freeing the entries in the list as we go. + */ +static void prune_refs(struct files_ref_store *refs, struct ref_to_prune **refs_to_prune) { - while (r) { + while (*refs_to_prune) { + struct ref_to_prune *r = *refs_to_prune; + *refs_to_prune = r->next; prune_ref(refs, r); - r = r->next; + free(r); } } @@@ -1087,16 -1527,12 +1087,16 @@@ static int files_pack_refs(struct ref_s files_downcast(ref_store, REF_STORE_WRITE | REF_STORE_ODB, "pack_refs"); struct ref_iterator *iter; - struct ref_dir *packed_refs; int ok; struct ref_to_prune *refs_to_prune = NULL; + struct strbuf err = STRBUF_INIT; + struct ref_transaction *transaction; + + transaction = ref_store_transaction_begin(refs->packed_ref_store, &err); + if (!transaction) + return -1; - lock_packed_refs(refs, LOCK_DIE_ON_ERROR); - packed_refs = get_packed_refs(refs); + packed_refs_lock(refs->packed_ref_store, LOCK_DIE_ON_ERROR, &err); iter = cache_ref_iterator_begin(get_loose_ref_cache(refs), NULL, 0); while ((ok = ref_iterator_advance(iter)) == ITER_OK) { @@@ -1105,19 -1541,29 +1105,19 @@@ * in the packed ref cache. If the reference should be * pruned, also add it to refs_to_prune. */ - struct ref_entry *packed_entry; - if (!should_pack_ref(iter->refname, iter->oid, iter->flags, flags)) continue; /* - * Create an entry in the packed-refs cache equivalent - * to the one from the loose ref cache, except that - * we don't copy the peeled status, because we want it - * to be re-peeled. + * Add a reference creation for this reference to the + * packed-refs transaction: */ - packed_entry = find_ref_entry(packed_refs, iter->refname); - if (packed_entry) { - /* Overwrite existing packed entry with info from loose entry */ - packed_entry->flag = REF_ISPACKED; - oidcpy(&packed_entry->u.value.oid, iter->oid); - } else { - packed_entry = create_ref_entry(iter->refname, iter->oid, - REF_ISPACKED); - add_ref_entry(packed_refs, packed_entry); - } - oidclr(&packed_entry->u.value.peeled); + if (ref_transaction_update(transaction, iter->refname, + iter->oid->hash, NULL, + REF_NODEREF, NULL, &err)) + die("failure preparing to create packed reference %s: %s", + iter->refname, err.buf); /* Schedule the loose reference for pruning if requested. */ if ((flags & PACK_REFS_PRUNE)) { @@@ -1131,16 -1577,67 +1131,16 @@@ if (ok != ITER_DONE) die("error while iterating over references"); - if (commit_packed_refs(refs)) - die_errno("unable to overwrite old ref-pack file"); - - prune_refs(refs, refs_to_prune); - return 0; -} - -/* - * Rewrite the packed-refs file, omitting any refs listed in - * 'refnames'. On error, leave packed-refs unchanged, write an error - * message to 'err', and return a nonzero value. - * - * The refs in 'refnames' needn't be sorted. `err` must not be NULL. - */ -static int repack_without_refs(struct files_ref_store *refs, - struct string_list *refnames, struct strbuf *err) -{ - struct ref_dir *packed; - struct string_list_item *refname; - int ret, needs_repacking = 0, removed = 0; - - files_assert_main_repository(refs, "repack_without_refs"); - assert(err); - - /* Look for a packed ref */ - for_each_string_list_item(refname, refnames) { - if (get_packed_ref(refs, refname->string)) { - needs_repacking = 1; - break; - } - } + if (ref_transaction_commit(transaction, &err)) + die("unable to write new packed-refs: %s", err.buf); - /* Avoid locking if we have nothing to do */ - if (!needs_repacking) - return 0; /* no refname exists in packed refs */ + ref_transaction_free(transaction); - if (lock_packed_refs(refs, 0)) { - unable_to_lock_message(files_packed_refs_path(refs), errno, err); - return -1; - } - packed = get_packed_refs(refs); + packed_refs_unlock(refs->packed_ref_store); - /* Remove refnames from the cache */ - for_each_string_list_item(refname, refnames) - if (remove_entry_from_dir(packed, refname->string) != -1) - removed = 1; - if (!removed) { - /* - * All packed entries disappeared while we were - * acquiring the lock. - */ - rollback_packed_refs(refs); - return 0; - } - - /* Write what remains */ - ret = commit_packed_refs(refs); - if (ret) - strbuf_addf(err, "unable to overwrite old ref-pack file: %s", - strerror(errno)); - return ret; + prune_refs(refs, &refs_to_prune); + strbuf_release(&err); + return 0; } static int files_delete_refs(struct ref_store *ref_store, const char *msg, @@@ -1154,16 -1651,24 +1154,16 @@@ if (!refnames->nr) return 0; - result = repack_without_refs(refs, refnames, &err); - if (result) { - /* - * If we failed to rewrite the packed-refs file, then - * it is unsafe to try to remove loose refs, because - * doing so might expose an obsolete packed value for - * a reference that might even point at an object that - * has been garbage collected. - */ - if (refnames->nr == 1) - error(_("could not delete reference %s: %s"), - refnames->items[0].string, err.buf); - else - error(_("could not delete references: %s"), err.buf); + if (packed_refs_lock(refs->packed_ref_store, 0, &err)) + goto error; - goto out; + if (refs_delete_refs(refs->packed_ref_store, msg, refnames, flags)) { + packed_refs_unlock(refs->packed_ref_store); + goto error; } + packed_refs_unlock(refs->packed_ref_store); + for (i = 0; i < refnames->nr; i++) { const char *refname = refnames->items[i].string; @@@ -1171,24 -1676,9 +1171,24 @@@ result |= error(_("could not remove reference %s"), refname); } -out: strbuf_release(&err); return result; + +error: + /* + * If we failed to rewrite the packed-refs file, then it is + * unsafe to try to remove loose refs, because doing so might + * expose an obsolete packed value for a reference that might + * even point at an object that has been garbage collected. + */ + if (refnames->nr == 1) + error(_("could not delete reference %s: %s"), + refnames->items[0].string, err.buf); + else + error(_("could not delete references: %s"), err.buf); + + strbuf_release(&err); + return -1; } /* @@@ -1402,16 -1892,16 +1402,16 @@@ static int files_rename_ref(struct ref_ return ret; } -static int close_ref(struct ref_lock *lock) +static int close_ref_gently(struct ref_lock *lock) { - if (close_lock_file(lock->lk)) + if (close_lock_file_gently(&lock->lk)) return -1; return 0; } static int commit_ref(struct ref_lock *lock) { - char *path = get_locked_file_path(lock->lk); + char *path = get_locked_file_path(&lock->lk); struct stat st; if (!lstat(path, &st) && S_ISDIR(st.st_mode)) { @@@ -1435,7 -1925,7 +1435,7 @@@ free(path); } - if (commit_lock_file(lock->lk)) + if (commit_lock_file(&lock->lk)) return -1; return 0; } @@@ -1549,7 -2039,7 +1549,7 @@@ static int log_ref_write_fd(int fd, con written = len <= maxlen ? write_in_full(fd, logrec, len) : -1; free(logrec); - if (written != len) + if (written < 0) return -1; return 0; @@@ -1627,12 -2117,12 +1627,12 @@@ static int write_ref_to_lockfile(struc unlock_ref(lock); return -1; } - fd = get_lock_file_fd(lock->lk); + fd = get_lock_file_fd(&lock->lk); - if (write_in_full(fd, oid_to_hex(oid), GIT_SHA1_HEXSZ) != GIT_SHA1_HEXSZ || - write_in_full(fd, &term, 1) != 1 || + if (write_in_full(fd, oid_to_hex(oid), GIT_SHA1_HEXSZ) < 0 || + write_in_full(fd, &term, 1) < 0 || - close_ref(lock) < 0) { + close_ref_gently(lock) < 0) { strbuf_addf(err, - "couldn't write '%s'", get_lock_file_path(lock->lk)); + "couldn't write '%s'", get_lock_file_path(&lock->lk)); unlock_ref(lock); return -1; } @@@ -1709,7 -2199,7 +1709,7 @@@ static int create_ref_symlink(struct re { int ret = -1; #ifndef NO_SYMLINK_HEAD - char *ref_path = get_locked_file_path(lock->lk); + char *ref_path = get_locked_file_path(&lock->lk); unlink(ref_path); ret = symlink(target, ref_path); free(ref_path); @@@ -1745,14 -2235,14 +1745,14 @@@ static int create_symref_locked(struct return 0; } - if (!fdopen_lock_file(lock->lk, "w")) + if (!fdopen_lock_file(&lock->lk, "w")) return error("unable to fdopen %s: %s", - lock->lk->tempfile.filename.buf, strerror(errno)); + lock->lk.tempfile->filename.buf, strerror(errno)); update_symref_reflog(refs, lock, refname, target, logmsg); /* no error check; commit_ref will check ferror */ - fprintf(lock->lk->tempfile.fp, "ref: %s\n", target); + fprintf(lock->lk.tempfile->fp, "ref: %s\n", target); if (commit_ref(lock) < 0) return error("unable to write symref for %s: %s", refname, strerror(errno)); @@@ -2059,63 -2549,23 +2059,63 @@@ static struct ref_iterator_vtable files files_reflog_iterator_abort }; -static struct ref_iterator *files_reflog_iterator_begin(struct ref_store *ref_store) +static struct ref_iterator *reflog_iterator_begin(struct ref_store *ref_store, + const char *gitdir) { - struct files_ref_store *refs = - files_downcast(ref_store, REF_STORE_READ, - "reflog_iterator_begin"); struct files_reflog_iterator *iter = xcalloc(1, sizeof(*iter)); struct ref_iterator *ref_iterator = &iter->base; struct strbuf sb = STRBUF_INIT; base_ref_iterator_init(ref_iterator, &files_reflog_iterator_vtable); - files_reflog_path(refs, &sb, NULL); + strbuf_addf(&sb, "%s/logs", gitdir); iter->dir_iterator = dir_iterator_begin(sb.buf); iter->ref_store = ref_store; strbuf_release(&sb); + return ref_iterator; } +static enum iterator_selection reflog_iterator_select( + struct ref_iterator *iter_worktree, + struct ref_iterator *iter_common, + void *cb_data) +{ + if (iter_worktree) { + /* + * We're a bit loose here. We probably should ignore + * common refs if they are accidentally added as + * per-worktree refs. + */ + return ITER_SELECT_0; + } else if (iter_common) { + if (ref_type(iter_common->refname) == REF_TYPE_NORMAL) + return ITER_SELECT_1; + + /* + * The main ref store may contain main worktree's + * per-worktree refs, which should be ignored + */ + return ITER_SKIP_1; + } else + return ITER_DONE; +} + +static struct ref_iterator *files_reflog_iterator_begin(struct ref_store *ref_store) +{ + struct files_ref_store *refs = + files_downcast(ref_store, REF_STORE_READ, + "reflog_iterator_begin"); + + if (!strcmp(refs->gitdir, refs->gitcommondir)) { + return reflog_iterator_begin(ref_store, refs->gitcommondir); + } else { + return merge_ref_iterator_begin( + reflog_iterator_begin(ref_store, refs->gitdir), + reflog_iterator_begin(ref_store, refs->gitcommondir), + reflog_iterator_select, refs); + } +} + /* * If update is a direct update of head_ref (the reference pointed to * by HEAD), then add an extra REF_LOG_ONLY update for HEAD. @@@ -2139,10 -2589,11 +2139,10 @@@ static int split_head_update(struct ref /* * First make sure that HEAD is not already in the - * transaction. This insertion is O(N) in the transaction + * transaction. This check is O(lg N) in the transaction * size, but it happens at most once per transaction. */ - item = string_list_insert(affected_refnames, "HEAD"); - if (item->util) { + if (string_list_has_string(affected_refnames, "HEAD")) { /* An entry already existed */ strbuf_addf(err, "multiple updates for 'HEAD' (including one " @@@ -2157,14 -2608,6 +2157,14 @@@ update->new_oid.hash, update->old_oid.hash, update->msg); + /* + * Add "HEAD". This insertion is O(N) in the transaction + * size, but it happens at most once per transaction. + * Add new_update->refname instead of a literal "HEAD". + */ + if (strcmp(new_update->refname, "HEAD")) + BUG("%s unexpectedly not 'HEAD'", new_update->refname); + item = string_list_insert(affected_refnames, new_update->refname); item->util = new_update; return 0; @@@ -2191,12 -2634,13 +2191,12 @@@ static int split_symref_update(struct f /* * First make sure that referent is not already in the - * transaction. This insertion is O(N) in the transaction + * transaction. This check is O(lg N) in the transaction * size, but it happens at most once per symref in a * transaction. */ - item = string_list_insert(affected_refnames, referent); - if (item->util) { - /* An entry already existed */ + if (string_list_has_string(affected_refnames, referent)) { + /* An entry already exists */ strbuf_addf(err, "multiple updates for '%s' (including one " "via symref '%s') are not allowed", @@@ -2231,17 -2675,6 +2231,17 @@@ update->flags |= REF_LOG_ONLY | REF_NODEREF; update->flags &= ~REF_HAVE_OLD; + /* + * Add the referent. This insertion is O(N) in the transaction + * size, but it happens at most once per symref in a + * transaction. Make sure to add new_update->refname, which will + * be valid as long as affected_refnames is in use, and NOT + * referent, which might soon be freed by our caller. + */ + item = string_list_insert(affected_refnames, new_update->refname); + if (item->util) + BUG("%s unexpectedly found in affected_refnames", + new_update->refname); item->util = new_update; return 0; @@@ -2313,7 -2746,7 +2313,7 @@@ static int lock_ref_for_update(struct f struct strbuf referent = STRBUF_INIT; int mustexist = (update->flags & REF_HAVE_OLD) && !is_null_oid(&update->old_oid); - int ret; + int ret = 0; struct ref_lock *lock; files_assert_main_repository(refs, "lock_ref_for_update"); @@@ -2325,7 -2758,7 +2325,7 @@@ ret = split_head_update(update, transaction, head_ref, affected_refnames, err); if (ret) - return ret; + goto out; } ret = lock_raw_ref(refs, update->refname, mustexist, @@@ -2339,7 -2772,7 +2339,7 @@@ strbuf_addf(err, "cannot lock ref '%s': %s", original_update_refname(update), reason); free(reason); - return ret; + goto out; } update->backend_data = lock; @@@ -2358,12 -2791,10 +2358,12 @@@ strbuf_addf(err, "cannot lock ref '%s': " "error reading reference", original_update_refname(update)); - return -1; + ret = TRANSACTION_GENERIC_ERROR; + goto out; } } else if (check_old_oid(update, &lock->old_oid, err)) { - return TRANSACTION_GENERIC_ERROR; + ret = TRANSACTION_GENERIC_ERROR; + goto out; } } else { /* @@@ -2377,15 -2808,13 +2377,15 @@@ referent.buf, transaction, affected_refnames, err); if (ret) - return ret; + goto out; } } else { struct ref_update *parent_update; - if (check_old_oid(update, &lock->old_oid, err)) - return TRANSACTION_GENERIC_ERROR; + if (check_old_oid(update, &lock->old_oid, err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto out; + } /* * If this update is happening indirectly because of a @@@ -2422,8 -2851,7 +2422,8 @@@ "cannot update ref '%s': %s", update->refname, write_err); free(write_err); - return TRANSACTION_GENERIC_ERROR; + ret = TRANSACTION_GENERIC_ERROR; + goto out; } else { update->flags |= REF_NEEDS_COMMIT; } @@@ -2434,35 -2862,22 +2434,35 @@@ * the lockfile is still open. Close it to * free up the file descriptor: */ - if (close_ref(lock)) { + if (close_ref_gently(lock)) { strbuf_addf(err, "couldn't close '%s.lock'", update->refname); - return TRANSACTION_GENERIC_ERROR; + ret = TRANSACTION_GENERIC_ERROR; + goto out; } } - return 0; + +out: + strbuf_release(&referent); + return ret; } +struct files_transaction_backend_data { + struct ref_transaction *packed_transaction; + int packed_refs_locked; +}; + /* * Unlock any references in `transaction` that are still locked, and * mark the transaction closed. */ -static void files_transaction_cleanup(struct ref_transaction *transaction) +static void files_transaction_cleanup(struct files_ref_store *refs, + struct ref_transaction *transaction) { size_t i; + struct files_transaction_backend_data *backend_data = + transaction->backend_data; + struct strbuf err = STRBUF_INIT; for (i = 0; i < transaction->nr; i++) { struct ref_update *update = transaction->updates[i]; @@@ -2474,17 -2889,6 +2474,17 @@@ } } + if (backend_data->packed_transaction && + ref_transaction_abort(backend_data->packed_transaction, &err)) { + error("error aborting transaction: %s", err.buf); + strbuf_release(&err); + } + + if (backend_data->packed_refs_locked) + packed_refs_unlock(refs->packed_ref_store); + + free(backend_data); + transaction->state = REF_TRANSACTION_CLOSED; } @@@ -2501,17 -2905,12 +2501,17 @@@ static int files_transaction_prepare(st char *head_ref = NULL; int head_type; struct object_id head_oid; + struct files_transaction_backend_data *backend_data; + struct ref_transaction *packed_transaction = NULL; assert(err); if (!transaction->nr) goto cleanup; + backend_data = xcalloc(1, sizeof(*backend_data)); + transaction->backend_data = backend_data; + /* * Fail if a refname appears more than once in the * transaction. (If we end up splitting up any updates using @@@ -2578,41 -2977,6 +2578,41 @@@ head_ref, &affected_refnames, err); if (ret) break; + + if (update->flags & REF_DELETING && + !(update->flags & REF_LOG_ONLY) && + !(update->flags & REF_ISPRUNING)) { + /* + * This reference has to be deleted from + * packed-refs if it exists there. + */ + if (!packed_transaction) { + packed_transaction = ref_store_transaction_begin( + refs->packed_ref_store, err); + if (!packed_transaction) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + + backend_data->packed_transaction = + packed_transaction; + } + + ref_transaction_add_update( + packed_transaction, update->refname, + update->flags & ~REF_HAVE_OLD, + update->new_oid.hash, update->old_oid.hash, + NULL); + } + } + + if (packed_transaction) { + if (packed_refs_lock(refs->packed_ref_store, 0, err)) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + backend_data->packed_refs_locked = 1; + ret = ref_transaction_prepare(packed_transaction, err); } cleanup: @@@ -2620,7 -2984,7 +2620,7 @@@ string_list_clear(&affected_refnames, 0); if (ret) - files_transaction_cleanup(transaction); + files_transaction_cleanup(refs, transaction); else transaction->state = REF_TRANSACTION_PREPARED; @@@ -2635,10 -2999,9 +2635,10 @@@ static int files_transaction_finish(str files_downcast(ref_store, 0, "ref_transaction_finish"); size_t i; int ret = 0; - struct string_list refs_to_delete = STRING_LIST_INIT_NODUP; - struct string_list_item *ref_to_delete; struct strbuf sb = STRBUF_INIT; + struct files_transaction_backend_data *backend_data; + struct ref_transaction *packed_transaction; + assert(err); @@@ -2647,9 -3010,6 +2647,9 @@@ return 0; } + backend_data = transaction->backend_data; + packed_transaction = backend_data->packed_transaction; + /* Perform updates first so live commits remain referenced */ for (i = 0; i < transaction->nr; i++) { struct ref_update *update = transaction->updates[i]; @@@ -2685,44 -3045,7 +2685,44 @@@ } } } - /* Perform deletes now that updates are safely completed */ + + /* + * Now that updates are safely completed, we can perform + * deletes. First delete the reflogs of any references that + * will be deleted, since (in the unexpected event of an + * error) leaving a reference without a reflog is less bad + * than leaving a reflog without a reference (the latter is a + * mildly invalid repository state): + */ + for (i = 0; i < transaction->nr; i++) { + struct ref_update *update = transaction->updates[i]; + if (update->flags & REF_DELETING && + !(update->flags & REF_LOG_ONLY) && + !(update->flags & REF_ISPRUNING)) { + strbuf_reset(&sb); + files_reflog_path(refs, &sb, update->refname); + if (!unlink_or_warn(sb.buf)) + try_remove_empty_parents(refs, update->refname, + REMOVE_EMPTY_PARENTS_REFLOG); + } + } + + /* + * Perform deletes now that updates are safely completed. + * + * First delete any packed versions of the references, while + * retaining the packed-refs lock: + */ + if (packed_transaction) { + ret = ref_transaction_commit(packed_transaction, err); + ref_transaction_free(packed_transaction); + packed_transaction = NULL; + backend_data->packed_transaction = NULL; + if (ret) + goto cleanup; + } + + /* Now delete the loose versions of the references: */ for (i = 0; i < transaction->nr; i++) { struct ref_update *update = transaction->updates[i]; struct ref_lock *lock = update->backend_data; @@@ -2740,13 -3063,31 +2740,13 @@@ } update->flags |= REF_DELETED_LOOSE; } - - if (!(update->flags & REF_ISPRUNING)) - string_list_append(&refs_to_delete, - lock->ref_name); } } - if (repack_without_refs(refs, &refs_to_delete, err)) { - ret = TRANSACTION_GENERIC_ERROR; - goto cleanup; - } - - /* Delete the reflogs of any references that were deleted: */ - for_each_string_list_item(ref_to_delete, &refs_to_delete) { - strbuf_reset(&sb); - files_reflog_path(refs, &sb, ref_to_delete->string); - if (!unlink_or_warn(sb.buf)) - try_remove_empty_parents(refs, ref_to_delete->string, - REMOVE_EMPTY_PARENTS_REFLOG); - } - clear_loose_ref_cache(refs); cleanup: - files_transaction_cleanup(transaction); + files_transaction_cleanup(refs, transaction); for (i = 0; i < transaction->nr; i++) { struct ref_update *update = transaction->updates[i]; @@@ -2764,6 -3105,7 +2764,6 @@@ } strbuf_release(&sb); - string_list_clear(&refs_to_delete, 0); return ret; } @@@ -2771,10 -3113,7 +2771,10 @@@ static int files_transaction_abort(stru struct ref_transaction *transaction, struct strbuf *err) { - files_transaction_cleanup(transaction); + struct files_ref_store *refs = + files_downcast(ref_store, 0, "ref_transaction_abort"); + + files_transaction_cleanup(refs, transaction); return 0; } @@@ -2796,7 -3135,6 +2796,7 @@@ static int files_initial_transaction_co size_t i; int ret = 0; struct string_list affected_refnames = STRING_LIST_INIT_NODUP; + struct ref_transaction *packed_transaction = NULL; assert(err); @@@ -2829,12 -3167,6 +2829,12 @@@ &affected_refnames)) die("BUG: initial ref transaction called with existing refs"); + packed_transaction = ref_store_transaction_begin(refs->packed_ref_store, err); + if (!packed_transaction) { + ret = TRANSACTION_GENERIC_ERROR; + goto cleanup; + } + for (i = 0; i < transaction->nr; i++) { struct ref_update *update = transaction->updates[i]; @@@ -2847,31 -3179,32 +2847,31 @@@ ret = TRANSACTION_NAME_CONFLICT; goto cleanup; } + + /* + * Add a reference creation for this reference to the + * packed-refs transaction: + */ + ref_transaction_add_update(packed_transaction, update->refname, + update->flags & ~REF_HAVE_OLD, + update->new_oid.hash, update->old_oid.hash, + NULL); } - if (lock_packed_refs(refs, 0)) { - strbuf_addf(err, "unable to lock packed-refs file: %s", - strerror(errno)); + if (packed_refs_lock(refs->packed_ref_store, 0, err)) { ret = TRANSACTION_GENERIC_ERROR; goto cleanup; } - for (i = 0; i < transaction->nr; i++) { - struct ref_update *update = transaction->updates[i]; - - if ((update->flags & REF_HAVE_NEW) && - !is_null_oid(&update->new_oid)) - add_packed_ref(refs, update->refname, - &update->new_oid); - } - - if (commit_packed_refs(refs)) { - strbuf_addf(err, "unable to commit packed-refs file: %s", - strerror(errno)); + if (initial_ref_transaction_commit(packed_transaction, err)) { ret = TRANSACTION_GENERIC_ERROR; goto cleanup; } cleanup: + if (packed_transaction) + ref_transaction_free(packed_transaction); + packed_refs_unlock(refs->packed_ref_store); transaction->state = REF_TRANSACTION_CLOSED; string_list_clear(&affected_refnames, 0); return ret; @@@ -3000,17 -3333,16 +3000,17 @@@ static int files_reflog_expire(struct r !(type & REF_ISSYMREF) && !is_null_oid(&cb.last_kept_oid); - if (close_lock_file(&reflog_lock)) { + if (close_lock_file_gently(&reflog_lock)) { status |= error("couldn't write %s: %s", log_file, strerror(errno)); + rollback_lock_file(&reflog_lock); } else if (update && - (write_in_full(get_lock_file_fd(lock->lk), + (write_in_full(get_lock_file_fd(&lock->lk), - oid_to_hex(&cb.last_kept_oid), GIT_SHA1_HEXSZ) != GIT_SHA1_HEXSZ || - write_str_in_full(get_lock_file_fd(&lock->lk), "\n") != 1 || + oid_to_hex(&cb.last_kept_oid), GIT_SHA1_HEXSZ) < 0 || - write_str_in_full(get_lock_file_fd(lock->lk), "\n") < 0 || - close_ref(lock) < 0)) { ++ write_str_in_full(get_lock_file_fd(&lock->lk), "\n") < 1 || + close_ref_gently(lock) < 0)) { status |= error("couldn't write %s", - get_lock_file_path(lock->lk)); + get_lock_file_path(&lock->lk)); rollback_lock_file(&reflog_lock); } else if (commit_lock_file(&reflog_lock)) { status |= error("unable to write reflog '%s' (%s)", diff --combined rerere.c index d77235645e,51376cf6da..1ce440f4bb --- a/rerere.c +++ b/rerere.c @@@ -258,7 -258,7 +258,7 @@@ static int write_rr(struct string_list rerere_id_hex(id), rr->items[i].string, 0); - if (write_in_full(out_fd, buf.buf, buf.len) != buf.len) + if (write_in_full(out_fd, buf.buf, buf.len) < 0) die("unable to write rerere record"); strbuf_release(&buf); @@@ -1133,14 -1133,14 +1133,14 @@@ int rerere_forget(struct pathspec *path * Garbage collection support */ -static time_t rerere_created_at(struct rerere_id *id) +static timestamp_t rerere_created_at(struct rerere_id *id) { struct stat st; return stat(rerere_path(id, "preimage"), &st) ? (time_t) 0 : st.st_mtime; } -static time_t rerere_last_used_at(struct rerere_id *id) +static timestamp_t rerere_last_used_at(struct rerere_id *id) { struct stat st; @@@ -1157,11 -1157,11 +1157,11 @@@ static void unlink_rr_item(struct rerer id->collection->status[id->variant] = 0; } -static void prune_one(struct rerere_id *id, time_t now, - int cutoff_resolve, int cutoff_noresolve) +static void prune_one(struct rerere_id *id, + timestamp_t cutoff_resolve, timestamp_t cutoff_noresolve) { - time_t then; - int cutoff; + timestamp_t then; + timestamp_t cutoff; then = rerere_last_used_at(id); if (then) @@@ -1172,7 -1172,7 +1172,7 @@@ return; cutoff = cutoff_noresolve; } - if (then < now - cutoff * 86400) + if (then < cutoff) unlink_rr_item(id); } @@@ -1182,15 -1182,15 +1182,15 @@@ void rerere_gc(struct string_list *rr DIR *dir; struct dirent *e; int i; - time_t now = time(NULL); - int cutoff_noresolve = 15; - int cutoff_resolve = 60; + timestamp_t now = time(NULL); + timestamp_t cutoff_noresolve = now - 15 * 86400; + timestamp_t cutoff_resolve = now - 60 * 86400; if (setup_rerere(rr, 0) < 0) return; - git_config_get_int("gc.rerereresolved", &cutoff_resolve); - git_config_get_int("gc.rerereunresolved", &cutoff_noresolve); + git_config_get_expiry_in_days("gc.rerereresolved", &cutoff_resolve, now); + git_config_get_expiry_in_days("gc.rerereunresolved", &cutoff_noresolve, now); git_config(git_default_config, NULL); dir = opendir(git_path("rr-cache")); if (!dir) @@@ -1211,7 -1211,7 +1211,7 @@@ for (id.variant = 0, id.collection = rr_dir; id.variant < id.collection->status_nr; id.variant++) { - prune_one(&id, now, cutoff_resolve, cutoff_noresolve); + prune_one(&id, cutoff_resolve, cutoff_noresolve); if (id.collection->status[id.variant]) now_empty = 0; } diff --combined sha1_file.c index b4a67bb838,20a9d39c00..dd7cbe52ef --- a/sha1_file.c +++ b/sha1_file.c @@@ -28,9 -28,11 +28,9 @@@ #include "list.h" #include "mergesort.h" #include "quote.h" +#include "packfile.h" -#define SZ_FMT PRIuMAX -static inline uintmax_t sz_fmt(size_t s) { return s; } - -const unsigned char null_sha1[20]; +const unsigned char null_sha1[GIT_MAX_RAWSZ]; const struct object_id null_oid; const struct object_id empty_tree_oid = { EMPTY_TREE_SHA1_BIN_LITERAL @@@ -276,6 -278,28 +276,6 @@@ static const char *alt_sha1_path(struc 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), ext); - return buf->buf; -} - -char *sha1_pack_name(const unsigned char *sha1) -{ - static struct strbuf buf = STRBUF_INIT; - return odb_pack_name(&buf, sha1, "pack"); -} - -char *sha1_pack_index_name(const unsigned char *sha1) -{ - static struct strbuf buf = STRBUF_INIT; - return odb_pack_name(&buf, sha1, "idx"); -} - struct alternate_object_database *alt_odb_list; static struct alternate_object_database **alt_odb_tail; @@@ -681,6 -705,213 +681,6 @@@ static int has_loose_object(const unsig return check_and_freshen(sha1, 0); } -static unsigned int pack_used_ctr; -static unsigned int pack_mmap_calls; -static unsigned int peak_pack_open_windows; -static unsigned int pack_open_windows; -static unsigned int pack_open_fds; -static unsigned int pack_max_fds; -static size_t peak_pack_mapped; -static size_t pack_mapped; -struct packed_git *packed_git; - -static struct mru packed_git_mru_storage; -struct mru *packed_git_mru = &packed_git_mru_storage; - -void pack_report(void) -{ - fprintf(stderr, - "pack_report: getpagesize() = %10" SZ_FMT "\n" - "pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n" - "pack_report: core.packedGitLimit = %10" SZ_FMT "\n", - sz_fmt(getpagesize()), - sz_fmt(packed_git_window_size), - sz_fmt(packed_git_limit)); - fprintf(stderr, - "pack_report: pack_used_ctr = %10u\n" - "pack_report: pack_mmap_calls = %10u\n" - "pack_report: pack_open_windows = %10u / %10u\n" - "pack_report: pack_mapped = " - "%10" SZ_FMT " / %10" SZ_FMT "\n", - pack_used_ctr, - pack_mmap_calls, - pack_open_windows, peak_pack_open_windows, - sz_fmt(pack_mapped), sz_fmt(peak_pack_mapped)); -} - -/* - * Open and mmap the index file at path, perform a couple of - * consistency checks, then record its information to p. Return 0 on - * success. - */ -static int check_packed_git_idx(const char *path, struct packed_git *p) -{ - void *idx_map; - struct pack_idx_header *hdr; - size_t idx_size; - uint32_t version, nr, i, *index; - int fd = git_open(path); - struct stat st; - - if (fd < 0) - return -1; - if (fstat(fd, &st)) { - close(fd); - return -1; - } - idx_size = xsize_t(st.st_size); - if (idx_size < 4 * 256 + 20 + 20) { - close(fd); - return error("index file %s is too small", path); - } - idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0); - close(fd); - - hdr = idx_map; - if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) { - version = ntohl(hdr->idx_version); - if (version < 2 || version > 2) { - munmap(idx_map, idx_size); - return error("index file %s is version %"PRIu32 - " and is not supported by this binary" - " (try upgrading GIT to a newer version)", - path, version); - } - } else - version = 1; - - nr = 0; - index = idx_map; - if (version > 1) - index += 2; /* skip index header */ - for (i = 0; i < 256; i++) { - uint32_t n = ntohl(index[i]); - if (n < nr) { - munmap(idx_map, idx_size); - return error("non-monotonic index %s", path); - } - nr = n; - } - - if (version == 1) { - /* - * Total size: - * - 256 index entries 4 bytes each - * - 24-byte entries * nr (20-byte sha1 + 4-byte offset) - * - 20-byte SHA1 of the packfile - * - 20-byte SHA1 file checksum - */ - if (idx_size != 4*256 + nr * 24 + 20 + 20) { - munmap(idx_map, idx_size); - return error("wrong index v1 file size in %s", path); - } - } else if (version == 2) { - /* - * Minimum size: - * - 8 bytes of header - * - 256 index entries 4 bytes each - * - 20-byte sha1 entry * nr - * - 4-byte crc entry * nr - * - 4-byte offset entry * nr - * - 20-byte SHA1 of the packfile - * - 20-byte SHA1 file checksum - * And after the 4-byte offset table might be a - * variable sized table containing 8-byte entries - * for offsets larger than 2^31. - */ - unsigned long min_size = 8 + 4*256 + nr*(20 + 4 + 4) + 20 + 20; - unsigned long max_size = min_size; - if (nr) - max_size += (nr - 1)*8; - if (idx_size < min_size || idx_size > max_size) { - munmap(idx_map, idx_size); - return error("wrong index v2 file size in %s", path); - } - if (idx_size != min_size && - /* - * make sure we can deal with large pack offsets. - * 31-bit signed offset won't be enough, neither - * 32-bit unsigned one will be. - */ - (sizeof(off_t) <= 4)) { - munmap(idx_map, idx_size); - return error("pack too large for current definition of off_t in %s", path); - } - } - - p->index_version = version; - p->index_data = idx_map; - p->index_size = idx_size; - p->num_objects = nr; - return 0; -} - -int open_pack_index(struct packed_git *p) -{ - char *idx_name; - size_t len; - int ret; - - if (p->index_data) - return 0; - - 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; -} - -static void scan_windows(struct packed_git *p, - struct packed_git **lru_p, - struct pack_window **lru_w, - struct pack_window **lru_l) -{ - struct pack_window *w, *w_l; - - for (w_l = NULL, w = p->windows; w; w = w->next) { - if (!w->inuse_cnt) { - if (!*lru_w || w->last_used < (*lru_w)->last_used) { - *lru_p = p; - *lru_w = w; - *lru_l = w_l; - } - } - w_l = w; - } -} - -static int unuse_one_window(struct packed_git *current) -{ - struct packed_git *p, *lru_p = NULL; - struct pack_window *lru_w = NULL, *lru_l = NULL; - - if (current) - scan_windows(current, &lru_p, &lru_w, &lru_l); - for (p = packed_git; p; p = p->next) - scan_windows(p, &lru_p, &lru_w, &lru_l); - if (lru_p) { - munmap(lru_w->base, lru_w->len); - pack_mapped -= lru_w->len; - if (lru_l) - lru_l->next = lru_w->next; - else - lru_p->windows = lru_w->next; - free(lru_w); - pack_open_windows--; - return 1; - } - return 0; -} - -void release_pack_memory(size_t need) -{ - size_t cur = pack_mapped; - while (need >= (cur - pack_mapped) && unuse_one_window(NULL)) - ; /* nothing */ -} - static void mmap_limit_check(size_t length) { static size_t limit = 0; @@@ -719,360 -950,1959 +719,360 @@@ void *xmmap(void *start, size_t length return ret; } -void close_pack_windows(struct packed_git *p) -{ - while (p->windows) { - struct pack_window *w = p->windows; - - if (w->inuse_cnt) - die("pack '%s' still has open windows to it", - p->pack_name); - munmap(w->base, w->len); - pack_mapped -= w->len; - pack_open_windows--; - p->windows = w->next; - free(w); - } -} - -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. + * With an in-core object data in "map", rehash it to make sure the + * object name actually matches "sha1" to detect object corruption. + * With "map" == NULL, try reading the object named with "sha1" using + * the streaming interface and rehash it to do the same. */ -static void find_lru_pack(struct packed_git *p, struct packed_git **lru_p, struct pack_window **mru_w, int *accept_windows_inuse) -{ - struct pack_window *w, *this_mru_w; - int has_windows_inuse = 0; - - /* - * Reject this pack if it has windows and the previously selected - * one does not. If this pack does not have windows, reject - * it if the pack file is newer than the previously selected one. - */ - if (*lru_p && !*mru_w && (p->windows || p->mtime > (*lru_p)->mtime)) - return; - - for (w = this_mru_w = p->windows; w; w = w->next) { - /* - * Reject this pack if any of its windows are in use, - * but the previously selected pack did not have any - * inuse windows. Otherwise, record that this pack - * has windows in use. - */ - if (w->inuse_cnt) { - if (*accept_windows_inuse) - has_windows_inuse = 1; - else - return; - } - - if (w->last_used > this_mru_w->last_used) - this_mru_w = w; - - /* - * Reject this pack if it has windows that have been - * used more recently than the previously selected pack. - * If the previously selected pack had windows inuse and - * we have not encountered a window in this pack that is - * inuse, skip this check since we prefer a pack with no - * inuse windows to one that has inuse windows. - */ - if (*mru_w && *accept_windows_inuse == has_windows_inuse && - this_mru_w->last_used > (*mru_w)->last_used) - return; - } - - /* - * Select this pack. - */ - *mru_w = this_mru_w; - *lru_p = p; - *accept_windows_inuse = has_windows_inuse; -} - -static int close_one_pack(void) +int check_sha1_signature(const unsigned char *sha1, void *map, + unsigned long size, const char *type) { - struct packed_git *p, *lru_p = NULL; - struct pack_window *mru_w = NULL; - int accept_windows_inuse = 1; + unsigned char real_sha1[20]; + enum object_type obj_type; + struct git_istream *st; + git_SHA_CTX c; + char hdr[32]; + int hdrlen; - for (p = packed_git; p; p = p->next) { - if (p->pack_fd == -1) - continue; - find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse); + if (map) { + hash_sha1_file(map, size, type, real_sha1); + return hashcmp(sha1, real_sha1) ? -1 : 0; } - if (lru_p) - return close_pack_fd(lru_p); + st = open_istream(sha1, &obj_type, &size, NULL); + if (!st) + return -1; - return 0; -} + /* Generate the header */ + hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(obj_type), size) + 1; -void unuse_pack(struct pack_window **w_cursor) -{ - struct pack_window *w = *w_cursor; - if (w) { - w->inuse_cnt--; - *w_cursor = NULL; - } -} + /* Sha1.. */ + git_SHA1_Init(&c); + git_SHA1_Update(&c, hdr, hdrlen); + for (;;) { + char buf[1024 * 16]; + ssize_t readlen = read_istream(st, buf, sizeof(buf)); -void close_pack_index(struct packed_git *p) -{ - if (p->index_data) { - munmap((void *)p->index_data, p->index_size); - p->index_data = NULL; + if (readlen < 0) { + close_istream(st); + return -1; + } + if (!readlen) + break; + git_SHA1_Update(&c, buf, readlen); } + git_SHA1_Final(real_sha1, &c); + close_istream(st); + return hashcmp(sha1, real_sha1) ? -1 : 0; } -static unsigned int get_max_fd_limit(void) +int git_open_cloexec(const char *name, int flags) { -#ifdef RLIMIT_NOFILE - { - struct rlimit lim; + int fd; + static int o_cloexec = O_CLOEXEC; - if (!getrlimit(RLIMIT_NOFILE, &lim)) - return lim.rlim_cur; + 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); } -#endif -#ifdef _SC_OPEN_MAX +#if defined(F_GETFD) && defined(F_SETFD) && defined(FD_CLOEXEC) { - long open_max = sysconf(_SC_OPEN_MAX); - if (0 < open_max) - return open_max; - /* - * Otherwise, we got -1 for one of the two - * reasons: - * - * (1) sysconf() did not understand _SC_OPEN_MAX - * and signaled an error with -1; or - * (2) sysconf() said there is no limit. - * - * We _could_ clear errno before calling sysconf() to - * tell these two cases apart and return a huge number - * in the latter case to let the caller cap it to a - * value that is not so selfish, but letting the - * fallback OPEN_MAX codepath take care of these cases - * is a lot simpler. - */ - } -#endif + static int fd_cloexec = FD_CLOEXEC; -#ifdef OPEN_MAX - return OPEN_MAX; -#else - return 1; /* see the caller ;-) */ + 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; + } + } #endif + return fd; } /* - * Do not call this directly as this leaks p->pack_fd on error return; - * call open_packed_git() instead. + * 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 open_packed_git_1(struct packed_git *p) +static int stat_sha1_file(const unsigned char *sha1, struct stat *st, + const char **path) { - struct stat st; - struct pack_header hdr; - unsigned char sha1[20]; - unsigned char *idx_sha1; - long fd_flag; - - if (!p->index_data && open_pack_index(p)) - return error("packfile %s index unavailable", p->pack_name); + struct alternate_object_database *alt; - if (!pack_max_fds) { - unsigned int max_fds = get_max_fd_limit(); + *path = sha1_file_name(sha1); + if (!lstat(*path, st)) + return 0; - /* Save 3 for stdin/stdout/stderr, 22 for work */ - if (25 < max_fds) - pack_max_fds = max_fds - 25; - else - pack_max_fds = 1; + prepare_alt_odb(); + errno = ENOENT; + for (alt = alt_odb_list; alt; alt = alt->next) { + *path = alt_sha1_path(alt, sha1); + if (!lstat(*path, st)) + return 0; } - while (pack_max_fds <= pack_open_fds && close_one_pack()) - ; /* nothing */ - - p->pack_fd = git_open(p->pack_name); - if (p->pack_fd < 0 || fstat(p->pack_fd, &st)) - return -1; - pack_open_fds++; - - /* If we created the struct before we had the pack we lack size. */ - if (!p->pack_size) { - if (!S_ISREG(st.st_mode)) - return error("packfile %s not a regular file", p->pack_name); - p->pack_size = st.st_size; - } else if (p->pack_size != st.st_size) - return error("packfile %s size changed", p->pack_name); - - /* We leave these file descriptors open with sliding mmap; - * there is no point keeping them open across exec(), though. - */ - fd_flag = fcntl(p->pack_fd, F_GETFD, 0); - if (fd_flag < 0) - return error("cannot determine file descriptor flags"); - fd_flag |= FD_CLOEXEC; - if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1) - return error("cannot set FD_CLOEXEC"); - - /* Verify we recognize this pack file format. */ - if (read_in_full(p->pack_fd, &hdr, sizeof(hdr)) != sizeof(hdr)) - return error("file %s is far too short to be a packfile", p->pack_name); - if (hdr.hdr_signature != htonl(PACK_SIGNATURE)) - return error("file %s is not a GIT packfile", p->pack_name); - if (!pack_version_ok(hdr.hdr_version)) - return error("packfile %s is version %"PRIu32" and not" - " supported (try upgrading GIT to a newer version)", - p->pack_name, ntohl(hdr.hdr_version)); - - /* Verify the pack matches its index. */ - if (p->num_objects != ntohl(hdr.hdr_entries)) - return error("packfile %s claims to have %"PRIu32" objects" - " while index indicates %"PRIu32" objects", - p->pack_name, ntohl(hdr.hdr_entries), - p->num_objects); - if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1) - return error("end of packfile %s is unavailable", p->pack_name); - if (read_in_full(p->pack_fd, sha1, sizeof(sha1)) != sizeof(sha1)) - return error("packfile %s signature is unavailable", p->pack_name); - idx_sha1 = ((unsigned char *)p->index_data) + p->index_size - 40; - if (hashcmp(sha1, idx_sha1)) - return error("packfile %s does not match index", p->pack_name); - return 0; -} - -static int open_packed_git(struct packed_git *p) -{ - if (!open_packed_git_1(p)) - return 0; - close_pack_fd(p); return -1; } -static int in_window(struct pack_window *win, off_t offset) +/* + * 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) { - /* We must promise at least 20 bytes (one hash) after the - * offset is available from this window, otherwise the offset - * is not actually in this window and a different window (which - * has that one hash excess) must be used. This is to support - * the object header and delta base parsing routines below. - */ - off_t win_off = win->offset; - return win_off <= offset - && (offset + 20) <= (win_off + win->len); -} + int fd; + struct alternate_object_database *alt; + int most_interesting_errno; -unsigned char *use_pack(struct packed_git *p, - struct pack_window **w_cursor, - off_t offset, - unsigned long *left) -{ - struct pack_window *win = *w_cursor; + *path = sha1_file_name(sha1); + fd = git_open(*path); + if (fd >= 0) + return fd; + most_interesting_errno = errno; - /* Since packfiles end in a hash of their content and it's - * pointless to ask for an offset into the middle of that - * hash, and the in_window function above wouldn't match - * don't allow an offset too close to the end of the file. - */ - if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p)) - die("packfile %s cannot be accessed", p->pack_name); - if (offset > (p->pack_size - 20)) - die("offset beyond end of packfile (truncated pack?)"); - if (offset < 0) - die(_("offset before end of packfile (broken .idx?)")); - - if (!win || !in_window(win, offset)) { - if (win) - win->inuse_cnt--; - for (win = p->windows; win; win = win->next) { - if (in_window(win, offset)) - break; - } - if (!win) { - size_t window_align = packed_git_window_size / 2; - off_t len; - - if (p->pack_fd == -1 && open_packed_git(p)) - die("packfile %s cannot be accessed", p->pack_name); - - win = xcalloc(1, sizeof(*win)); - win->offset = (offset / window_align) * window_align; - len = p->pack_size - win->offset; - if (len > packed_git_window_size) - len = packed_git_window_size; - win->len = (size_t)len; - pack_mapped += win->len; - while (packed_git_limit < pack_mapped - && unuse_one_window(p)) - ; /* nothing */ - win->base = xmmap(NULL, win->len, - PROT_READ, MAP_PRIVATE, - p->pack_fd, win->offset); - if (win->base == MAP_FAILED) - die_errno("packfile %s cannot be mapped", - p->pack_name); - if (!win->offset && win->len == p->pack_size - && !p->do_not_close) - close_pack_fd(p); - pack_mmap_calls++; - pack_open_windows++; - if (pack_mapped > peak_pack_mapped) - peak_pack_mapped = pack_mapped; - if (pack_open_windows > peak_pack_open_windows) - peak_pack_open_windows = pack_open_windows; - win->next = p->windows; - p->windows = win; - } - } - if (win != *w_cursor) { - win->last_used = pack_used_ctr++; - win->inuse_cnt++; - *w_cursor = win; + prepare_alt_odb(); + for (alt = alt_odb_list; alt; alt = alt->next) { + *path = alt_sha1_path(alt, sha1); + fd = git_open(*path); + if (fd >= 0) + return fd; + if (most_interesting_errno == ENOENT) + most_interesting_errno = errno; } - offset -= win->offset; - if (left) - *left = win->len - xsize_t(offset); - return win->base + offset; + errno = most_interesting_errno; + return -1; } -static struct packed_git *alloc_packed_git(int extra) +/* + * 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) { - struct packed_git *p = xmalloc(st_add(sizeof(*p), extra)); - memset(p, 0, sizeof(*p)); - p->pack_fd = -1; - return p; -} - -static void try_to_free_pack_memory(size_t size) -{ - release_pack_memory(size); -} - -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; - size_t alloc; - struct packed_git *p; - - if (!have_set_try_to_free_routine) { - have_set_try_to_free_routine = 1; - set_try_to_free_routine(try_to_free_pack_memory); - } - - /* - * Make sure a corresponding .pack file exists and that - * the index looks sane. - */ - 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 = st_add3(path_len, strlen(".pack"), 1); - p = alloc_packed_git(alloc); - memcpy(p->pack_name, path, path_len); - - xsnprintf(p->pack_name + path_len, alloc - path_len, ".keep"); - if (!access(p->pack_name, F_OK)) - p->pack_keep = 1; - - 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; - } - - /* ok, it looks sane as far as we can check without - * actually mapping the pack file. - */ - p->pack_size = st.st_size; - p->pack_local = local; - p->mtime = st.st_mtime; - if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1)) - hashclr(p->sha1); - return p; -} - -struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path) -{ - const char *path = sha1_pack_name(sha1); - size_t alloc = st_add(strlen(path), 1); - struct packed_git *p = alloc_packed_git(alloc); - - memcpy(p->pack_name, path, alloc); /* includes NUL */ - hashcpy(p->sha1, sha1); - if (check_packed_git_idx(idx_path, p)) { - free(p); - return NULL; - } - - return p; -} - -void install_packed_git(struct packed_git *pack) -{ - if (pack->pack_fd != -1) - pack_open_fds++; - - pack->next = packed_git; - packed_git = pack; -} - -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) -{ - if (seen_bits == (PACKDIR_FILE_PACK|PACKDIR_FILE_IDX)) - return; - - for (; first < last; first++) - report_garbage(seen_bits, list->items[first].string); -} - -static void report_pack_garbage(struct string_list *list) -{ - int i, baselen = -1, first = 0, seen_bits = 0; - - if (!report_garbage) - return; - - string_list_sort(list); - - for (i = 0; i < list->nr; i++) { - const char *path = list->items[i].string; - if (baselen != -1 && - strncmp(path, list->items[first].string, baselen)) { - report_helper(list, seen_bits, first, i); - baselen = -1; - seen_bits = 0; - } - if (baselen == -1) { - const char *dot = strrchr(path, '.'); - if (!dot) { - report_garbage(PACKDIR_FILE_GARBAGE, path); - continue; - } - baselen = dot - path + 1; - first = i; - } - if (!strcmp(path + baselen, "pack")) - seen_bits |= 1; - else if (!strcmp(path + baselen, "idx")) - seen_bits |= 2; - } - report_helper(list, seen_bits, first, list->nr); -} - -static void prepare_packed_git_one(char *objdir, int local) -{ - struct strbuf path = STRBUF_INIT; - size_t dirnamelen; - DIR *dir; - struct dirent *de; - struct string_list garbage = STRING_LIST_INIT_DUP; - - strbuf_addstr(&path, objdir); - strbuf_addstr(&path, "/pack"); - dir = opendir(path.buf); - if (!dir) { - if (errno != ENOENT) - error_errno("unable to open object pack directory: %s", - path.buf); - strbuf_release(&path); - return; - } - strbuf_addch(&path, '/'); - dirnamelen = path.len; - while ((de = readdir(dir)) != NULL) { - struct packed_git *p; - size_t base_len; - - if (is_dot_or_dotdot(de->d_name)) - continue; - - strbuf_setlen(&path, dirnamelen); - strbuf_addstr(&path, de->d_name); - - base_len = path.len; - if (strip_suffix_mem(path.buf, &base_len, ".idx")) { - /* Don't reopen a pack we already have. */ - for (p = packed_git; p; p = p->next) { - size_t len; - if (strip_suffix(p->pack_name, ".pack", &len) && - len == base_len && - !memcmp(p->pack_name, path.buf, len)) - break; - } - if (p == NULL && - /* - * See if it really is a valid .idx file with - * corresponding .pack file that we can map. - */ - (p = add_packed_git(path.buf, path.len, local)) != NULL) - install_packed_git(p); - } - - if (!report_garbage) - continue; - - if (ends_with(de->d_name, ".idx") || - ends_with(de->d_name, ".pack") || - ends_with(de->d_name, ".bitmap") || - ends_with(de->d_name, ".keep")) - string_list_append(&garbage, path.buf); - else - report_garbage(PACKDIR_FILE_GARBAGE, path.buf); - } - closedir(dir); - report_pack_garbage(&garbage); - string_list_clear(&garbage, 0); - 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; -} - -static void set_next_packed_git(void *p, void *next) -{ - ((struct packed_git *)p)->next = next; -} - -static int sort_pack(const void *a_, const void *b_) -{ - const struct packed_git *a = a_; - const struct packed_git *b = b_; - int st; - - /* - * Local packs tend to contain objects specific to our - * variant of the project than remote ones. In addition, - * remote ones could be on a network mounted filesystem. - * Favor local ones for these reasons. - */ - st = a->pack_local - b->pack_local; - if (st) - return -st; - - /* - * Younger packs tend to contain more recent objects, - * and more recent objects tend to get accessed more - * often. - */ - if (a->mtime < b->mtime) - return 1; - else if (a->mtime == b->mtime) - return 0; - return -1; -} - -static void rearrange_packed_git(void) -{ - packed_git = llist_mergesort(packed_git, get_next_packed_git, - set_next_packed_git, sort_pack); -} - -static void prepare_packed_git_mru(void) -{ - struct packed_git *p; - - mru_clear(packed_git_mru); - for (p = packed_git; p; p = p->next) - mru_append(packed_git_mru, p); -} - -static int prepare_packed_git_run_once = 0; -void prepare_packed_git(void) -{ - struct alternate_object_database *alt; - - if (prepare_packed_git_run_once) - return; - prepare_packed_git_one(get_object_directory(), 1); - prepare_alt_odb(); - 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; -} - -void reprepare_packed_git(void) -{ - approximate_object_count_valid = 0; - prepare_packed_git_run_once = 0; - prepare_packed_git(); -} - -static void mark_bad_packed_object(struct packed_git *p, - const unsigned char *sha1) -{ - unsigned i; - for (i = 0; i < p->num_bad_objects; i++) - if (!hashcmp(sha1, p->bad_object_sha1 + GIT_SHA1_RAWSZ * i)) - return; - p->bad_object_sha1 = xrealloc(p->bad_object_sha1, - 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++; -} - -static const struct packed_git *has_packed_and_bad(const unsigned char *sha1) -{ - struct packed_git *p; - unsigned i; - - for (p = packed_git; p; p = p->next) - for (i = 0; i < p->num_bad_objects; i++) - if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) - return p; - return NULL; -} - -/* - * With an in-core object data in "map", rehash it to make sure the - * object name actually matches "sha1" to detect object corruption. - * With "map" == NULL, try reading the object named with "sha1" using - * the streaming interface and rehash it to do the same. - */ -int check_sha1_signature(const unsigned char *sha1, void *map, - unsigned long size, const char *type) -{ - unsigned char real_sha1[20]; - enum object_type obj_type; - struct git_istream *st; - git_SHA_CTX c; - char hdr[32]; - int hdrlen; - - if (map) { - hash_sha1_file(map, size, type, real_sha1); - return hashcmp(sha1, real_sha1) ? -1 : 0; - } - - st = open_istream(sha1, &obj_type, &size, NULL); - if (!st) - return -1; - - /* Generate the header */ - hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(obj_type), size) + 1; - - /* Sha1.. */ - git_SHA1_Init(&c); - git_SHA1_Update(&c, hdr, hdrlen); - for (;;) { - char buf[1024 * 16]; - ssize_t readlen = read_istream(st, buf, sizeof(buf)); - - if (readlen < 0) { - close_istream(st); - return -1; - } - if (!readlen) - break; - git_SHA1_Update(&c, buf, readlen); - } - git_SHA1_Final(real_sha1, &c); - close_istream(st); - return hashcmp(sha1, real_sha1) ? -1 : 0; -} - -int git_open_cloexec(const char *name, int flags) -{ - int fd; - static int o_cloexec = O_CLOEXEC; - - 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); - } - -#if defined(F_GETFD) && defined(F_SETFD) && defined(FD_CLOEXEC) - { - static int fd_cloexec = FD_CLOEXEC; - - 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; - } - } -#endif - return fd; -} - -/* - * 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; - - *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) { - *path = alt_sha1_path(alt, sha1); - if (!lstat(*path, st)) - return 0; - } - - return -1; -} - -/* - * 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; - - *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) { - *path = alt_sha1_path(alt, sha1); - fd = git_open(*path); - if (fd >= 0) - return fd; - if (most_interesting_errno == ENOENT) - most_interesting_errno = errno; - } - errno = most_interesting_errno; - return -1; -} - -/* - * 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; - - if (path) - fd = git_open(path); - else - fd = open_sha1_file(sha1, &path); - map = NULL; - if (fd >= 0) { - struct stat st; - - if (!fstat(fd, &st)) { - *size = xsize_t(st.st_size); - if (!*size) { - /* mmap() is forbidden on empty files */ - error("object file %s is empty", path); - return NULL; - } - map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0); - } - close(fd); - } - 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) -{ - unsigned shift; - unsigned long size, c; - unsigned long used = 0; - - c = buf[used++]; - *type = (c >> 4) & 7; - size = c & 15; - shift = 4; - while (c & 0x80) { - if (len <= used || bitsizeof(long) <= shift) { - error("bad object header"); - size = used = 0; - break; - } - c = buf[used++]; - size += (c & 0x7f) << shift; - shift += 7; - } - *sizep = size; - return used; -} - -static int unpack_sha1_short_header(git_zstream *stream, - unsigned char *map, unsigned long mapsize, - void *buffer, unsigned long bufsiz) -{ - /* Get the data stream */ - memset(stream, 0, sizeof(*stream)); - stream->next_in = map; - stream->avail_in = mapsize; - stream->next_out = buffer; - stream->avail_out = bufsiz; - - git_inflate_init(stream); - return git_inflate(stream, 0); -} - -int unpack_sha1_header(git_zstream *stream, - unsigned char *map, unsigned long mapsize, - void *buffer, unsigned long bufsiz) -{ - int status = unpack_sha1_short_header(stream, map, mapsize, - buffer, bufsiz); - - if (status < Z_OK) - return status; - - /* Make sure we have the terminating NUL */ - if (!memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer)) - return -1; - return 0; -} - -static int unpack_sha1_header_to_strbuf(git_zstream *stream, unsigned char *map, - unsigned long mapsize, void *buffer, - unsigned long bufsiz, struct strbuf *header) -{ - int status; - - status = unpack_sha1_short_header(stream, map, mapsize, buffer, bufsiz); - if (status < Z_OK) - return -1; - - /* - * Check if entire header is unpacked in the first iteration. - */ - if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer)) - return 0; - - /* - * buffer[0..bufsiz] was not large enough. Copy the partial - * result out to header, and then append the result of further - * reading the stream. - */ - strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer); - stream->next_out = buffer; - stream->avail_out = bufsiz; - - do { - status = git_inflate(stream, 0); - strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer); - if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer)) - return 0; - stream->next_out = buffer; - stream->avail_out = bufsiz; - } while (status != Z_STREAM_END); - return -1; -} - -static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1) -{ - int bytes = strlen(buffer) + 1; - unsigned char *buf = xmallocz(size); - unsigned long n; - int status = Z_OK; - - n = stream->total_out - bytes; - if (n > size) - n = size; - memcpy(buf, (char *) buffer + bytes, n); - bytes = n; - if (bytes <= size) { - /* - * The above condition must be (bytes <= size), not - * (bytes < size). In other words, even though we - * expect no more output and set avail_out to zero, - * the input zlib stream may have bytes that express - * "this concludes the stream", and we *do* want to - * eat that input. - * - * Otherwise we would not be able to test that we - * consumed all the input to reach the expected size; - * we also want to check that zlib tells us that all - * went well with status == Z_STREAM_END at the end. - */ - stream->next_out = buf + bytes; - stream->avail_out = size - bytes; - while (status == Z_OK) - status = git_inflate(stream, Z_FINISH); - } - if (status == Z_STREAM_END && !stream->avail_in) { - git_inflate_end(stream); - return buf; - } - - if (status < 0) - error("corrupt loose object '%s'", sha1_to_hex(sha1)); - else if (stream->avail_in) - error("garbage at end of loose object '%s'", - sha1_to_hex(sha1)); - free(buf); - return NULL; -} - -/* - * We used to just use "sscanf()", but that's actually way - * too permissive for what we want to check. So do an anal - * object header parse by hand. - */ -static int parse_sha1_header_extended(const char *hdr, struct object_info *oi, - unsigned int flags) -{ - const char *type_buf = hdr; - unsigned long size; - int type, type_len = 0; - - /* - * The type can be of any size but is followed by - * a space. - */ - for (;;) { - char c = *hdr++; - if (!c) - return -1; - if (c == ' ') - break; - type_len++; - } - - type = type_from_string_gently(type_buf, type_len, 1); - if (oi->typename) - strbuf_add(oi->typename, type_buf, type_len); - /* - * Set type to 0 if its an unknown object and - * we're obtaining the type using '--allow-unknown-type' - * option. - */ - if ((flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE) && (type < 0)) - type = 0; - else if (type < 0) - die("invalid object type"); - if (oi->typep) - *oi->typep = type; - - /* - * The length must follow immediately, and be in canonical - * decimal format (ie "010" is not valid). - */ - size = *hdr++ - '0'; - if (size > 9) - return -1; - if (size) { - for (;;) { - unsigned long c = *hdr - '0'; - if (c > 9) - break; - hdr++; - size = size * 10 + c; - } - } - - if (oi->sizep) - *oi->sizep = size; - - /* - * The length must be followed by a zero byte - */ - return *hdr ? -1 : type; -} - -int parse_sha1_header(const char *hdr, unsigned long *sizep) -{ - struct object_info oi = OBJECT_INFO_INIT; - - oi.sizep = sizep; - return parse_sha1_header_extended(hdr, &oi, 0); -} - -unsigned long get_size_from_delta(struct packed_git *p, - struct pack_window **w_curs, - off_t curpos) -{ - const unsigned char *data; - unsigned char delta_head[20], *in; - git_zstream stream; - int st; - - memset(&stream, 0, sizeof(stream)); - stream.next_out = delta_head; - stream.avail_out = sizeof(delta_head); - - 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); - curpos += stream.next_in - in; - } while ((st == Z_OK || st == Z_BUF_ERROR) && - stream.total_out < sizeof(delta_head)); - git_inflate_end(&stream); - if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) { - error("delta data unpack-initial failed"); - return 0; - } - - /* Examine the initial part of the delta to figure out - * the result size. - */ - data = delta_head; - - /* ignore base size */ - get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); - - /* Read the result size */ - return get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); -} - -static off_t get_delta_base(struct packed_git *p, - struct pack_window **w_curs, - off_t *curpos, - enum object_type type, - off_t delta_obj_offset) -{ - unsigned char *base_info = use_pack(p, w_curs, *curpos, NULL); - off_t base_offset; - - /* use_pack() assured us we have [base_info, base_info + 20) - * as a range that we can look at without walking off the - * end of the mapped window. Its actually the hash size - * that is assured. An OFS_DELTA longer than the hash size - * is stupid, as then a REF_DELTA would be smaller to store. - */ - if (type == OBJ_OFS_DELTA) { - unsigned used = 0; - unsigned char c = base_info[used++]; - base_offset = c & 127; - while (c & 128) { - base_offset += 1; - if (!base_offset || MSB(base_offset, 7)) - return 0; /* overflow */ - c = base_info[used++]; - base_offset = (base_offset << 7) + (c & 127); - } - base_offset = delta_obj_offset - base_offset; - if (base_offset <= 0 || base_offset >= delta_obj_offset) - return 0; /* out of bound */ - *curpos += used; - } else if (type == OBJ_REF_DELTA) { - /* The base entry _must_ be in the same pack */ - base_offset = find_pack_entry_one(base_info, p); - *curpos += 20; - } else - die("I am totally screwed"); - return base_offset; -} - -/* - * Like get_delta_base above, but we return the sha1 instead of the pack - * offset. This means it is cheaper for REF deltas (we do not have to do - * the final object lookup), but more expensive for OFS deltas (we - * have to load the revidx to convert the offset back into a sha1). - */ -static const unsigned char *get_delta_base_sha1(struct packed_git *p, - struct pack_window **w_curs, - off_t curpos, - enum object_type type, - off_t delta_obj_offset) -{ - if (type == OBJ_REF_DELTA) { - unsigned char *base = use_pack(p, w_curs, curpos, NULL); - return base; - } else if (type == OBJ_OFS_DELTA) { - struct revindex_entry *revidx; - off_t base_offset = get_delta_base(p, w_curs, &curpos, - type, delta_obj_offset); - - if (!base_offset) - return NULL; - - revidx = find_pack_revindex(p, base_offset); - if (!revidx) - return NULL; - - return nth_packed_object_sha1(p, revidx->nr); - } else - return NULL; -} - -int unpack_object_header(struct packed_git *p, - struct pack_window **w_curs, - off_t *curpos, - unsigned long *sizep) -{ - unsigned char *base; - unsigned long left; - unsigned long used; - enum object_type type; - - /* use_pack() assures us we have [base, base + 20) available - * as a range that we can look at. (Its actually the hash - * size that is assured.) With our object header encoding - * the maximum deflated object size is 2^137, which is just - * insane, so we know won't exceed what we have been given. - */ - base = use_pack(p, w_curs, *curpos, &left); - used = unpack_object_header_buffer(base, left, &type, sizep); - if (!used) { - type = OBJ_BAD; - } else - *curpos += used; - - return type; -} - -static int retry_bad_packed_offset(struct packed_git *p, off_t obj_offset) -{ - int type; - struct revindex_entry *revidx; - const unsigned char *sha1; - revidx = find_pack_revindex(p, obj_offset); - if (!revidx) - return OBJ_BAD; - sha1 = nth_packed_object_sha1(p, revidx->nr); - mark_bad_packed_object(p, sha1); - type = sha1_object_info(sha1, NULL); - if (type <= OBJ_NONE) - return OBJ_BAD; - return type; -} - -#define POI_STACK_PREALLOC 64 - -static enum object_type packed_to_object_type(struct packed_git *p, - off_t obj_offset, - enum object_type type, - struct pack_window **w_curs, - off_t curpos) -{ - off_t small_poi_stack[POI_STACK_PREALLOC]; - off_t *poi_stack = small_poi_stack; - int poi_stack_nr = 0, poi_stack_alloc = POI_STACK_PREALLOC; - - while (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) { - off_t base_offset; - unsigned long size; - /* Push the object we're going to leave behind */ - if (poi_stack_nr >= poi_stack_alloc && poi_stack == small_poi_stack) { - poi_stack_alloc = alloc_nr(poi_stack_nr); - ALLOC_ARRAY(poi_stack, poi_stack_alloc); - memcpy(poi_stack, small_poi_stack, sizeof(off_t)*poi_stack_nr); - } else { - ALLOC_GROW(poi_stack, poi_stack_nr+1, poi_stack_alloc); - } - poi_stack[poi_stack_nr++] = obj_offset; - /* If parsing the base offset fails, just unwind */ - base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset); - if (!base_offset) - goto unwind; - curpos = obj_offset = base_offset; - type = unpack_object_header(p, w_curs, &curpos, &size); - if (type <= OBJ_NONE) { - /* If getting the base itself fails, we first - * retry the base, otherwise unwind */ - type = retry_bad_packed_offset(p, base_offset); - if (type > OBJ_NONE) - goto out; - goto unwind; - } - } - - switch (type) { - case OBJ_BAD: - case OBJ_COMMIT: - case OBJ_TREE: - case OBJ_BLOB: - case OBJ_TAG: - break; - default: - error("unknown object type %i at offset %"PRIuMAX" in %s", - type, (uintmax_t)obj_offset, p->pack_name); - type = OBJ_BAD; - } - -out: - if (poi_stack != small_poi_stack) - free(poi_stack); - return type; - -unwind: - while (poi_stack_nr) { - obj_offset = poi_stack[--poi_stack_nr]; - type = retry_bad_packed_offset(p, obj_offset); - if (type > OBJ_NONE) - goto out; - } - type = OBJ_BAD; - goto out; -} - -static struct hashmap delta_base_cache; -static size_t delta_base_cached; - -static LIST_HEAD(delta_base_cache_lru); - -struct delta_base_cache_key { - struct packed_git *p; - off_t base_offset; -}; - -struct delta_base_cache_entry { - struct hashmap hash; - struct delta_base_cache_key key; - struct list_head lru; - void *data; - unsigned long size; - enum object_type type; -}; - -static unsigned int pack_entry_hash(struct packed_git *p, off_t base_offset) -{ - unsigned int hash; - - hash = (unsigned int)(intptr_t)p + (unsigned int)base_offset; - hash += (hash >> 8) + (hash >> 16); - return hash; -} - -static struct delta_base_cache_entry * -get_delta_base_cache_entry(struct packed_git *p, off_t base_offset) -{ - struct hashmap_entry entry; - struct delta_base_cache_key key; - - if (!delta_base_cache.cmpfn) - return NULL; - - hashmap_entry_init(&entry, pack_entry_hash(p, base_offset)); - key.p = p; - key.base_offset = base_offset; - return hashmap_get(&delta_base_cache, &entry, &key); -} - -static int delta_base_cache_key_eq(const struct delta_base_cache_key *a, - const struct delta_base_cache_key *b) -{ - return a->p == b->p && a->base_offset == b->base_offset; -} + void *map; + int fd; -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; - const struct delta_base_cache_key *key = vkey; - if (key) - return !delta_base_cache_key_eq(&a->key, key); + if (path) + fd = git_open(path); else - return !delta_base_cache_key_eq(&a->key, &b->key); -} - -static int in_delta_base_cache(struct packed_git *p, off_t base_offset) -{ - return !!get_delta_base_cache_entry(p, base_offset); -} - -/* - * Remove the entry from the cache, but do _not_ free the associated - * entry data. The caller takes ownership of the "data" buffer, and - * should copy out any fields it wants before detaching. - */ -static void detach_delta_base_cache_entry(struct delta_base_cache_entry *ent) -{ - hashmap_remove(&delta_base_cache, ent, &ent->key); - list_del(&ent->lru); - delta_base_cached -= ent->size; - free(ent); -} - -static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset, - unsigned long *base_size, enum object_type *type) -{ - struct delta_base_cache_entry *ent; - - ent = get_delta_base_cache_entry(p, base_offset); - if (!ent) - return unpack_entry(p, base_offset, type, base_size); - - if (type) - *type = ent->type; - if (base_size) - *base_size = ent->size; - return xmemdupz(ent->data, ent->size); -} - -static inline void release_delta_base_cache(struct delta_base_cache_entry *ent) -{ - free(ent->data); - detach_delta_base_cache_entry(ent); -} - -void clear_delta_base_cache(void) -{ - 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); - } -} - -static void add_delta_base_cache(struct packed_git *p, off_t base_offset, - void *base, unsigned long base_size, enum object_type type) -{ - struct delta_base_cache_entry *ent = xmalloc(sizeof(*ent)); - struct list_head *lru, *tmp; - - delta_base_cached += base_size; - - list_for_each_safe(lru, tmp, &delta_base_cache_lru) { - struct delta_base_cache_entry *f = - list_entry(lru, struct delta_base_cache_entry, lru); - if (delta_base_cached <= delta_base_cache_limit) - break; - release_delta_base_cache(f); - } - - ent->key.p = p; - ent->key.base_offset = base_offset; - ent->type = type; - ent->data = base; - ent->size = base_size; - list_add_tail(&ent->lru, &delta_base_cache_lru); - - if (!delta_base_cache.cmpfn) - 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); - } - -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); - -static void write_pack_access_log(struct packed_git *p, off_t obj_offset) -{ - static struct trace_key pack_access = TRACE_KEY_INIT(PACK_ACCESS); - trace_printf_key(&pack_access, "%s %"PRIuMAX"\n", - p->pack_name, (uintmax_t)obj_offset); -} - -int do_check_packed_object_crc; - -#define UNPACK_ENTRY_STACK_PREALLOC 64 -struct unpack_entry_stack_ent { - off_t obj_offset; - off_t curpos; - unsigned long size; -}; - -void *unpack_entry(struct packed_git *p, off_t obj_offset, - enum object_type *final_type, unsigned long *final_size) -{ - struct pack_window *w_curs = NULL; - off_t curpos = obj_offset; - void *data = NULL; - unsigned long size; - enum object_type type; - struct unpack_entry_stack_ent small_delta_stack[UNPACK_ENTRY_STACK_PREALLOC]; - struct unpack_entry_stack_ent *delta_stack = small_delta_stack; - int delta_stack_nr = 0, delta_stack_alloc = UNPACK_ENTRY_STACK_PREALLOC; - int base_from_cache = 0; - - write_pack_access_log(p, obj_offset); - - /* PHASE 1: drill down to the innermost base object */ - for (;;) { - off_t base_offset; - int i; - struct delta_base_cache_entry *ent; - - ent = get_delta_base_cache_entry(p, curpos); - if (ent) { - type = ent->type; - data = ent->data; - size = ent->size; - detach_delta_base_cache_entry(ent); - base_from_cache = 1; - break; - } - - if (do_check_packed_object_crc && p->index_version > 1) { - struct revindex_entry *revidx = find_pack_revindex(p, obj_offset); - off_t len = revidx[1].offset - obj_offset; - if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) { - const unsigned char *sha1 = - nth_packed_object_sha1(p, revidx->nr); - error("bad packed object CRC for %s", - sha1_to_hex(sha1)); - mark_bad_packed_object(p, sha1); - data = NULL; - goto out; - } - } - - type = unpack_object_header(p, &w_curs, &curpos, &size); - if (type != OBJ_OFS_DELTA && type != OBJ_REF_DELTA) - break; - - base_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset); - if (!base_offset) { - error("failed to validate delta base reference " - "at offset %"PRIuMAX" from %s", - (uintmax_t)curpos, p->pack_name); - /* bail to phase 2, in hopes of recovery */ - data = NULL; - break; - } - - /* push object, proceed to base */ - if (delta_stack_nr >= delta_stack_alloc - && delta_stack == small_delta_stack) { - delta_stack_alloc = alloc_nr(delta_stack_nr); - ALLOC_ARRAY(delta_stack, delta_stack_alloc); - memcpy(delta_stack, small_delta_stack, - sizeof(*delta_stack)*delta_stack_nr); - } else { - ALLOC_GROW(delta_stack, delta_stack_nr+1, delta_stack_alloc); - } - i = delta_stack_nr++; - delta_stack[i].obj_offset = obj_offset; - delta_stack[i].curpos = curpos; - delta_stack[i].size = size; - - curpos = obj_offset = base_offset; - } - - /* PHASE 2: handle the base */ - switch (type) { - case OBJ_OFS_DELTA: - case OBJ_REF_DELTA: - if (data) - die("BUG: unpack_entry: left loop at a valid delta"); - break; - case OBJ_COMMIT: - case OBJ_TREE: - case OBJ_BLOB: - case OBJ_TAG: - if (!base_from_cache) - data = unpack_compressed_entry(p, &w_curs, curpos, size); - break; - default: - data = NULL; - error("unknown object type %i at offset %"PRIuMAX" in %s", - type, (uintmax_t)obj_offset, p->pack_name); - } - - /* PHASE 3: apply deltas in order */ - - /* invariants: - * 'data' holds the base data, or NULL if there was corruption - */ - while (delta_stack_nr) { - void *delta_data; - void *base = data; - void *external_base = NULL; - unsigned long delta_size, base_size = size; - int i; - - data = NULL; - - if (base) - add_delta_base_cache(p, obj_offset, base, base_size, type); - - if (!base) { - /* - * We're probably in deep shit, but let's try to fetch - * the required base anyway from another pack or loose. - * This is costly but should happen only in the presence - * of a corrupted pack, and is better than failing outright. - */ - struct revindex_entry *revidx; - const unsigned char *base_sha1; - revidx = find_pack_revindex(p, obj_offset); - if (revidx) { - base_sha1 = nth_packed_object_sha1(p, revidx->nr); - error("failed to read delta base object %s" - " at offset %"PRIuMAX" from %s", - sha1_to_hex(base_sha1), (uintmax_t)obj_offset, - p->pack_name); - mark_bad_packed_object(p, base_sha1); - base = read_object(base_sha1, &type, &base_size); - external_base = base; - } - } - - i = --delta_stack_nr; - obj_offset = delta_stack[i].obj_offset; - curpos = delta_stack[i].curpos; - delta_size = delta_stack[i].size; - - if (!base) - continue; - - delta_data = unpack_compressed_entry(p, &w_curs, curpos, delta_size); - - if (!delta_data) { - error("failed to unpack compressed delta " - "at offset %"PRIuMAX" from %s", - (uintmax_t)curpos, p->pack_name); - data = NULL; - free(external_base); - continue; - } - - data = patch_delta(base, base_size, - delta_data, delta_size, - &size); - - /* - * We could not apply the delta; warn the user, but keep going. - * Our failure will be noticed either in the next iteration of - * the loop, or if this is the final delta, in the caller when - * we return NULL. Those code paths will take care of making - * a more explicit warning and retrying with another copy of - * the object. - */ - if (!data) - error("failed to apply delta"); - - free(delta_data); - free(external_base); - } - - if (final_type) - *final_type = type; - if (final_size) - *final_size = size; - -out: - unuse_pack(&w_curs); - - if (delta_stack != small_delta_stack) - free(delta_stack); - - return data; -} + fd = open_sha1_file(sha1, &path); + map = NULL; + if (fd >= 0) { + struct stat st; -const unsigned char *nth_packed_object_sha1(struct packed_git *p, - uint32_t n) -{ - const unsigned char *index = p->index_data; - if (!index) { - if (open_pack_index(p)) - return NULL; - index = p->index_data; - } - if (n >= p->num_objects) - return NULL; - index += 4 * 256; - if (p->index_version == 1) { - return index + 24 * n + 4; - } else { - index += 8; - return index + 20 * n; + if (!fstat(fd, &st)) { + *size = xsize_t(st.st_size); + if (!*size) { + /* mmap() is forbidden on empty files */ + error("object file %s is empty", path); + return NULL; + } + map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0); + } + close(fd); } + return map; } -const struct object_id *nth_packed_object_oid(struct object_id *oid, - struct packed_git *p, - uint32_t n) +void *map_sha1_file(const unsigned char *sha1, unsigned long *size) { - const unsigned char *hash = nth_packed_object_sha1(p, n); - if (!hash) - return NULL; - hashcpy(oid->hash, hash); - return oid; + return map_sha1_file_1(NULL, sha1, size); } -void check_pack_index_ptr(const struct packed_git *p, const void *vptr) +static int unpack_sha1_short_header(git_zstream *stream, + unsigned char *map, unsigned long mapsize, + void *buffer, unsigned long bufsiz) { - const unsigned char *ptr = vptr; - const unsigned char *start = p->index_data; - const unsigned char *end = start + p->index_size; - if (ptr < start) - die(_("offset before start of pack index for %s (corrupt index?)"), - p->pack_name); - /* No need to check for underflow; .idx files must be at least 8 bytes */ - if (ptr >= end - 8) - die(_("offset beyond end of pack index for %s (truncated index?)"), - p->pack_name); -} + /* Get the data stream */ + memset(stream, 0, sizeof(*stream)); + stream->next_in = map; + stream->avail_in = mapsize; + stream->next_out = buffer; + stream->avail_out = bufsiz; -off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n) -{ - const unsigned char *index = p->index_data; - index += 4 * 256; - if (p->index_version == 1) { - return ntohl(*((uint32_t *)(index + 24 * n))); - } else { - uint32_t off; - index += 8 + p->num_objects * (20 + 4); - off = ntohl(*((uint32_t *)(index + 4 * n))); - if (!(off & 0x80000000)) - return off; - index += p->num_objects * 4 + (off & 0x7fffffff) * 8; - check_pack_index_ptr(p, index); - return (((uint64_t)ntohl(*((uint32_t *)(index + 0)))) << 32) | - ntohl(*((uint32_t *)(index + 4))); - } + git_inflate_init(stream); + return git_inflate(stream, 0); } -off_t find_pack_entry_one(const unsigned char *sha1, - struct packed_git *p) +int unpack_sha1_header(git_zstream *stream, + unsigned char *map, unsigned long mapsize, + void *buffer, unsigned long bufsiz) { - 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) - debug_lookup = !!getenv("GIT_DEBUG_LOOKUP"); - - if (!index) { - if (open_pack_index(p)) - return 0; - level1_ofs = p->index_data; - index = p->index_data; - } - if (p->index_version > 1) { - level1_ofs += 2; - index += 8; - } - index += 4 * 256; - hi = ntohl(level1_ofs[*sha1]); - lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1])); - if (p->index_version > 1) { - stride = 20; - } else { - stride = 24; - index += 4; - } - - if (debug_lookup) - printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n", - sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects); + int status = unpack_sha1_short_header(stream, map, mapsize, + buffer, bufsiz); - 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); - } + if (status < Z_OK) + return status; - while (lo < hi) { - unsigned mi = (lo + hi) / 2; - int cmp = hashcmp(index + mi * stride, sha1); - - if (debug_lookup) - printf("lo %u hi %u rg %u mi %u\n", - lo, hi, hi - lo, mi); - if (!cmp) - return nth_packed_object_offset(p, mi); - if (cmp > 0) - hi = mi; - else - lo = mi+1; - } + /* Make sure we have the terminating NUL */ + if (!memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer)) + return -1; return 0; } -int is_pack_valid(struct packed_git *p) +static int unpack_sha1_header_to_strbuf(git_zstream *stream, unsigned char *map, + unsigned long mapsize, void *buffer, + unsigned long bufsiz, struct strbuf *header) { - /* An already open pack is known to be valid. */ - if (p->pack_fd != -1) - return 1; + int status; + + status = unpack_sha1_short_header(stream, map, mapsize, buffer, bufsiz); + if (status < Z_OK) + return -1; - /* If the pack has one window completely covering the - * file size, the pack is known to be valid even if - * the descriptor is not currently open. + /* + * Check if entire header is unpacked in the first iteration. */ - if (p->windows) { - struct pack_window *w = p->windows; + if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer)) + return 0; - if (!w->offset && w->len == p->pack_size) - return 1; - } + /* + * buffer[0..bufsiz] was not large enough. Copy the partial + * result out to header, and then append the result of further + * reading the stream. + */ + strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer); + stream->next_out = buffer; + stream->avail_out = bufsiz; - /* Force the pack to open to prove its valid. */ - return !open_packed_git(p); + do { + status = git_inflate(stream, 0); + strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer); + if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer)) + return 0; + stream->next_out = buffer; + stream->avail_out = bufsiz; + } while (status != Z_STREAM_END); + return -1; } -static int fill_pack_entry(const unsigned char *sha1, - struct pack_entry *e, - struct packed_git *p) +static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1) { - off_t offset; + int bytes = strlen(buffer) + 1; + unsigned char *buf = xmallocz(size); + unsigned long n; + int status = Z_OK; - if (p->num_bad_objects) { - unsigned i; - for (i = 0; i < p->num_bad_objects; i++) - if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) - return 0; + n = stream->total_out - bytes; + if (n > size) + n = size; + memcpy(buf, (char *) buffer + bytes, n); + bytes = n; + if (bytes <= size) { + /* + * The above condition must be (bytes <= size), not + * (bytes < size). In other words, even though we + * expect no more output and set avail_out to zero, + * the input zlib stream may have bytes that express + * "this concludes the stream", and we *do* want to + * eat that input. + * + * Otherwise we would not be able to test that we + * consumed all the input to reach the expected size; + * we also want to check that zlib tells us that all + * went well with status == Z_STREAM_END at the end. + */ + stream->next_out = buf + bytes; + stream->avail_out = size - bytes; + while (status == Z_OK) + status = git_inflate(stream, Z_FINISH); + } + if (status == Z_STREAM_END && !stream->avail_in) { + git_inflate_end(stream); + return buf; } - offset = find_pack_entry_one(sha1, p); - if (!offset) - return 0; - - /* - * We are about to tell the caller where they can locate the - * requested object. We better make sure the packfile is - * still here and can be accessed before supplying that - * answer, as it may have been deleted since the index was - * loaded! - */ - if (!is_pack_valid(p)) - return 0; - e->offset = offset; - e->p = p; - hashcpy(e->sha1, sha1); - return 1; + if (status < 0) + error("corrupt loose object '%s'", sha1_to_hex(sha1)); + else if (stream->avail_in) + error("garbage at end of loose object '%s'", + sha1_to_hex(sha1)); + free(buf); + return NULL; } /* - * Iff a pack file contains the object named by sha1, return true and - * store its location to e. + * We used to just use "sscanf()", but that's actually way + * too permissive for what we want to check. So do an anal + * object header parse by hand. */ -static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e) +static int parse_sha1_header_extended(const char *hdr, struct object_info *oi, + unsigned int flags) { - struct mru_entry *p; + const char *type_buf = hdr; + unsigned long size; + int type, type_len = 0; - prepare_packed_git(); - if (!packed_git) - return 0; + /* + * The type can be of any size but is followed by + * a space. + */ + for (;;) { + char c = *hdr++; + if (!c) + return -1; + if (c == ' ') + break; + type_len++; + } - for (p = packed_git_mru->head; p; p = p->next) { - if (fill_pack_entry(sha1, e, p->item)) { - mru_mark(packed_git_mru, p); - return 1; + type = type_from_string_gently(type_buf, type_len, 1); + if (oi->typename) + strbuf_add(oi->typename, type_buf, type_len); + /* + * Set type to 0 if its an unknown object and + * we're obtaining the type using '--allow-unknown-type' + * option. + */ + if ((flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE) && (type < 0)) + type = 0; + else if (type < 0) + die("invalid object type"); + if (oi->typep) + *oi->typep = type; + + /* + * The length must follow immediately, and be in canonical + * decimal format (ie "010" is not valid). + */ + size = *hdr++ - '0'; + if (size > 9) + return -1; + if (size) { + for (;;) { + unsigned long c = *hdr - '0'; + if (c > 9) + break; + hdr++; + size = size * 10 + c; } } - return 0; + + if (oi->sizep) + *oi->sizep = size; + + /* + * The length must be followed by a zero byte + */ + return *hdr ? -1 : type; } -struct packed_git *find_sha1_pack(const unsigned char *sha1, - struct packed_git *packs) +int parse_sha1_header(const char *hdr, unsigned long *sizep) { - struct packed_git *p; - - for (p = packs; p; p = p->next) { - if (find_pack_entry_one(sha1, p)) - return p; - } - return NULL; + struct object_info oi = OBJECT_INFO_INIT; + oi.sizep = sizep; + return parse_sha1_header_extended(hdr, &oi, 0); } static int sha1_loose_object_info(const unsigned char *sha1, @@@ -1145,7 -2975,6 +1145,7 @@@ if (oi->sizep == &size_scratch) oi->sizep = NULL; strbuf_release(&hdrbuf); + oi->whence = OI_LOOSE; return (status < 0) ? status : 0; } @@@ -1183,8 -3012,10 +1183,8 @@@ int sha1_object_info_extended(const uns 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. */ if (flags & OBJECT_INFO_QUICK) { @@@ -1207,7 -3038,10 +1207,7 @@@ if (rtype < 0) { mark_bad_packed_object(e.p, real); 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 || @@@ -1231,18 -3065,28 +1231,18 @@@ int sha1_object_info(const unsigned cha return type; } -static void *read_packed_sha1(const unsigned char *sha1, - enum object_type *type, unsigned long *size) +static void *read_object(const unsigned char *sha1, enum object_type *type, + unsigned long *size) { - struct pack_entry e; - void *data; + struct object_info oi = OBJECT_INFO_INIT; + void *content; + oi.typep = type; + oi.sizep = size; + oi.contentp = &content; - if (!find_pack_entry(sha1, &e)) + if (sha1_object_info_extended(sha1, &oi, 0) < 0) 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; + return content; } int pretend_sha1_file(void *buf, unsigned long len, enum object_type type, @@@ -1263,6 -3107,20 +1263,6 @@@ return 0; } -static void *read_object(const unsigned char *sha1, enum object_type *type, - unsigned long *size) -{ - struct object_info oi = OBJECT_INFO_INIT; - void *content; - oi.typep = type; - oi.sizep = size; - oi.contentp = &content; - - if (sha1_object_info_extended(sha1, &oi, 0) < 0) - return NULL; - return content; -} - /* * This function dies on corrupt objects; the callers who want to * deal with them should arrange to call read_object() and give error @@@ -1581,7 -3439,7 +1581,7 @@@ int write_sha1_file(const void *buf, un } int hash_sha1_file_literally(const void *buf, unsigned long len, const char *type, - unsigned char *sha1, unsigned flags) + struct object_id *oid, unsigned flags) { char *header; int hdrlen, status = 0; @@@ -1589,13 -3447,13 +1589,13 @@@ /* type string, SP, %lu of the length plus NUL must fit this */ hdrlen = strlen(type) + 32; header = xmalloc(hdrlen); - write_sha1_file_prepare(buf, len, type, sha1, header, &hdrlen); + write_sha1_file_prepare(buf, len, type, oid->hash, header, &hdrlen); if (!(flags & HASH_WRITE_OBJECT)) goto cleanup; - if (freshen_packed_object(sha1) || freshen_loose_object(sha1)) + if (freshen_packed_object(oid->hash) || freshen_loose_object(oid->hash)) goto cleanup; - status = write_loose_object(sha1, header, hdrlen, buf, len, 0); + status = write_loose_object(oid->hash, header, hdrlen, buf, len, 0); cleanup: free(header); @@@ -1613,7 -3471,7 +1613,7 @@@ 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; @@@ -1623,6 -3481,20 +1623,6 @@@ return ret; } -int has_pack_index(const unsigned char *sha1) -{ - struct stat st; - if (stat(sha1_pack_index_name(sha1), &st)) - return 0; - return 1; -} - -int has_sha1_pack(const unsigned char *sha1) -{ - struct pack_entry e; - return find_pack_entry(sha1, &e); -} - int has_sha1_file_with_flags(const unsigned char *sha1, int flags) { if (!startup_info->have_repository) @@@ -1785,14 -3657,14 +1785,14 @@@ static int index_core(unsigned char *sh * binary blobs, they generally do not want to get any conversion, and * callers should avoid this code path when filters are requested. */ -static int index_stream(unsigned char *sha1, int fd, size_t size, +static int index_stream(struct object_id *oid, int fd, size_t size, enum object_type type, const char *path, unsigned flags) { - return index_bulk_checkin(sha1, fd, size, type, path, flags); + return index_bulk_checkin(oid->hash, fd, size, type, path, flags); } -int index_fd(unsigned char *sha1, int fd, struct stat *st, +int index_fd(struct object_id *oid, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags) { int ret; @@@ -1802,32 -3674,31 +1802,32 @@@ * die() for large files. */ if (type == OBJ_BLOB && path && would_convert_to_git_filter_fd(path)) - ret = index_stream_convert_blob(sha1, fd, path, flags); + ret = index_stream_convert_blob(oid->hash, fd, path, flags); else if (!S_ISREG(st->st_mode)) - ret = index_pipe(sha1, fd, type, path, flags); + ret = index_pipe(oid->hash, fd, type, path, flags); else if (st->st_size <= big_file_threshold || type != OBJ_BLOB || (path && would_convert_to_git(&the_index, path))) - ret = index_core(sha1, fd, xsize_t(st->st_size), type, path, + ret = index_core(oid->hash, fd, xsize_t(st->st_size), type, path, flags); else - ret = index_stream(sha1, fd, xsize_t(st->st_size), type, path, + ret = index_stream(oid, fd, xsize_t(st->st_size), type, path, flags); close(fd); return ret; } -int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags) +int index_path(struct object_id *oid, const char *path, struct stat *st, unsigned flags) { int fd; struct strbuf sb = STRBUF_INIT; + int rc = 0; switch (st->st_mode & S_IFMT) { case S_IFREG: fd = open(path, O_RDONLY); if (fd < 0) return error_errno("open(\"%s\")", path); - if (index_fd(sha1, fd, st, OBJ_BLOB, path, flags) < 0) + if (index_fd(oid, fd, st, OBJ_BLOB, path, flags) < 0) return error("%s: failed to insert into database", path); break; @@@ -1835,22 -3706,23 +1835,22 @@@ if (strbuf_readlink(&sb, path, st->st_size)) return error_errno("readlink(\"%s\")", path); if (!(flags & HASH_WRITE_OBJECT)) - hash_sha1_file(sb.buf, sb.len, blob_type, sha1); - else if (write_sha1_file(sb.buf, sb.len, blob_type, sha1)) - return error("%s: failed to insert into database", - path); + hash_sha1_file(sb.buf, sb.len, blob_type, oid->hash); + else if (write_sha1_file(sb.buf, sb.len, blob_type, oid->hash)) + rc = error("%s: failed to insert into database", path); strbuf_release(&sb); break; case S_IFDIR: - return resolve_gitlink_ref(path, "HEAD", sha1); + return resolve_gitlink_ref(path, "HEAD", oid->hash); default: return error("%s: unsupported file type", path); } - return 0; + return rc; } int read_pack_header(int fd, struct pack_header *header) { - if (read_in_full(fd, header, sizeof(*header)) < sizeof(*header)) + if (read_in_full(fd, header, sizeof(*header)) != sizeof(*header)) /* "eof before pack header was fully read" */ return PH_ERROR_EOF; @@@ -2015,6 -3887,46 +2015,6 @@@ int for_each_loose_object(each_loose_ob return foreach_alt_odb(loose_from_alt_odb, &alt); } -static int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn cb, void *data) -{ - uint32_t i; - int r = 0; - - for (i = 0; i < p->num_objects; i++) { - struct object_id oid; - - 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(&oid, p, i, data); - if (r) - break; - } - return r; -} - -int for_each_packed_object(each_packed_object_fn cb, void *data, unsigned flags) -{ - struct packed_git *p; - int r = 0; - int pack_errors = 0; - - prepare_packed_git(); - for (p = packed_git; p; p = p->next) { - if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local) - continue; - if (open_pack_index(p)) { - pack_errors = 1; - continue; - } - r = for_each_object_in_pack(p, cb, data); - if (r) - break; - } - return r ? r : pack_errors; -} - static int check_stream_sha1(git_zstream *stream, const char *hdr, unsigned long size, diff --combined shallow.c index 1cc1c76415,e8429a9a84..eabb65d3a7 --- a/shallow.c +++ b/shallow.c @@@ -107,7 -107,7 +107,7 @@@ struct commit_list *get_shallow_commits cur_depth++; if ((depth != INFINITE_DEPTH && cur_depth >= depth) || (is_repository_shallow() && !commit->parents && - (graft = lookup_commit_graft(commit->object.oid.hash)) != NULL && + (graft = lookup_commit_graft(&commit->object.oid)) != NULL && graft->nr_parent < 0)) { commit_list_insert(commit, &result); commit->object.flags |= shallow_flag; @@@ -286,26 -286,28 +286,26 @@@ int write_shallow_commits(struct strbu return write_shallow_commits_1(out, use_pack_protocol, extra, 0); } -static struct tempfile temporary_shallow; - const char *setup_temporary_shallow(const struct oid_array *extra) { + struct tempfile *temp; struct strbuf sb = STRBUF_INIT; - int fd; if (write_shallow_commits(&sb, 0, extra)) { - fd = xmks_tempfile(&temporary_shallow, git_path("shallow_XXXXXX")); + temp = xmks_tempfile(git_path("shallow_XXXXXX")); - if (write_in_full(temp->fd, sb.buf, sb.len) != sb.len || - if (write_in_full(fd, sb.buf, sb.len) < 0) ++ if (write_in_full(temp->fd, sb.buf, sb.len) < 0 || + close_tempfile_gently(temp) < 0) die_errno("failed to write to %s", - get_tempfile_path(&temporary_shallow)); - close_tempfile(&temporary_shallow); + get_tempfile_path(temp)); strbuf_release(&sb); - return get_tempfile_path(&temporary_shallow); + return get_tempfile_path(temp); } /* * is_repository_shallow() sees empty string as "no shallow * file". */ - return get_tempfile_path(&temporary_shallow); + return ""; } void setup_alternate_shallow(struct lock_file *shallow_lock, @@@ -319,7 -321,7 +319,7 @@@ LOCK_DIE_ON_ERROR); check_shallow_file_for_update(); if (write_shallow_commits(&sb, 0, extra)) { - if (write_in_full(fd, sb.buf, sb.len) != sb.len) + if (write_in_full(fd, sb.buf, sb.len) < 0) die_errno("failed to write to %s", get_lock_file_path(shallow_lock)); *alternate_shallow_file = get_lock_file_path(shallow_lock); @@@ -366,7 -368,7 +366,7 @@@ void prune_shallow(int show_only LOCK_DIE_ON_ERROR); check_shallow_file_for_update(); if (write_shallow_commits_1(&sb, 0, NULL, SEEN_ONLY)) { - if (write_in_full(fd, sb.buf, sb.len) != sb.len) + if (write_in_full(fd, sb.buf, sb.len) < 0) die_errno("failed to write to %s", get_lock_file_path(&shallow_lock)); commit_lock_file(&shallow_lock); @@@ -396,7 -398,7 +396,7 @@@ void prepare_shallow_info(struct shallo for (i = 0; i < sa->nr; i++) { if (has_object_file(sa->oid + i)) { struct commit_graft *graft; - graft = lookup_commit_graft(sa->oid[i].hash); + graft = lookup_commit_graft(&sa->oid[i]); if (graft && graft->nr_parent < 0) continue; info->ours[info->nr_ours++] = i; diff --combined streaming.c index 6f1c60f12b,c8b85e4498..5892b50bd8 --- a/streaming.c +++ b/streaming.c @@@ -3,7 -3,6 +3,7 @@@ */ #include "cache.h" #include "streaming.h" +#include "packfile.h" enum input_source { stream_error = -1, @@@ -540,7 -539,7 +540,7 @@@ int stream_blob_to_fd(int fd, const str kept = 0; wrote = write_in_full(fd, buf, readlen); - if (wrote != readlen) + if (wrote < 0) goto close_and_exit; } if (kept && (lseek(fd, kept - 1, SEEK_CUR) == (off_t) -1 || diff --combined transport-helper.c index 42b960ff86,2128a32f1c..c948d5215c --- a/transport-helper.c +++ b/transport-helper.c @@@ -44,8 -44,7 +44,7 @@@ static void sendline(struct helper_dat { if (debug) fprintf(stderr, "Debug: Remote helper: -> %s", buffer->buf); - if (write_in_full(helper->helper->in, buffer->buf, buffer->len) - != buffer->len) + if (write_in_full(helper->helper->in, buffer->buf, buffer->len) < 0) die_errno("Full write to remote helper failed"); } @@@ -74,7 -73,7 +73,7 @@@ static void write_constant(int fd, cons { if (debug) fprintf(stderr, "Debug: Remote helper: -> %s", str); - if (write_in_full(fd, str, strlen(str)) != strlen(str)) + if (write_in_full(fd, str, strlen(str)) < 0) die_errno("Full write to remote helper failed"); } @@@ -604,7 -603,6 +603,7 @@@ static int process_connect_service(stru cmdbuf.buf); exit: + strbuf_release(&cmdbuf); fclose(input); return ret; } @@@ -928,7 -926,7 +927,7 @@@ static int push_refs_with_export(struc struct object_id oid; private = apply_refspecs(data->refspecs, data->refspec_nr, ref->name); - if (private && !get_sha1(private, oid.hash)) { + if (private && !get_oid(private, &oid)) { strbuf_addf(&buf, "^%s", private); string_list_append(&revlist_args, strbuf_detach(&buf, NULL)); oidcpy(&ref->old_oid, &oid); @@@ -1118,13 -1116,6 +1117,13 @@@ int transport_helper_init(struct transp __attribute__((format (printf, 1, 2))) static void transfer_debug(const char *fmt, ...) { + /* + * NEEDSWORK: This function is sometimes used from multiple threads, and + * we end up using debug_enabled racily. That "should not matter" since + * we always write the same value, but it's still wrong. This function + * is listed in .tsan-suppressions for the time being. + */ + va_list args; char msgbuf[PBUFFERSIZE]; static int debug_enabled = -1;