From dad4f23ce59339bb32ad9e1cc1682c696f7a724f Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Tue, 18 Aug 2020 22:58:25 +0000 Subject: [PATCH 1/2] dir: make clear_directory() free all relevant memory The calling convention for the dir API is supposed to end with a call to clear_directory() to free up no longer needed memory. However, clear_directory() didn't free dir->entries or dir->ignored. I believe this was an oversight, but a number of callers noticed memory leaks and started free'ing these. Unfortunately, they did so somewhat haphazardly (sometimes freeing the entries in the arrays, and sometimes only free'ing the arrays themselves). This suggests the callers weren't trying to make sure any possible memory used might be free'd, but just the memory they noticed their usecase definitely had allocated. Fix this mess by moving all the duplicated free'ing logic into clear_directory(). End by resetting dir to a pristine state so it could be reused if desired. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- builtin/clean.c | 6 +----- builtin/stash.c | 3 --- dir.c | 13 +++++++++++-- dir.h | 2 +- wt-status.c | 4 ---- 5 files changed, 13 insertions(+), 15 deletions(-) diff --git a/builtin/clean.c b/builtin/clean.c index 5a9c29a558..4ffe00dd7f 100644 --- a/builtin/clean.c +++ b/builtin/clean.c @@ -1021,11 +1021,7 @@ int cmd_clean(int argc, const char **argv, const char *prefix) string_list_append(&del_list, rel); } - for (i = 0; i < dir.nr; i++) - free(dir.entries[i]); - - for (i = 0; i < dir.ignored_nr; i++) - free(dir.ignored[i]); + clear_directory(&dir); if (interactive && del_list.nr > 0) interactive_main_loop(); diff --git a/builtin/stash.c b/builtin/stash.c index 10d87630cd..da48533d49 100644 --- a/builtin/stash.c +++ b/builtin/stash.c @@ -875,11 +875,8 @@ static int get_untracked_files(const struct pathspec *ps, int include_untracked, strbuf_addstr(untracked_files, ent->name); /* NUL-terminate: will be fed to update-index -z */ strbuf_addch(untracked_files, '\0'); - free(ent); } - free(dir.entries); - free(dir.ignored); clear_directory(&dir); return found; } diff --git a/dir.c b/dir.c index fe64be30ed..aa96030031 100644 --- a/dir.c +++ b/dir.c @@ -3009,8 +3009,8 @@ int remove_path(const char *name) } /* - * Frees memory within dir which was allocated for exclude lists and - * the exclude_stack. Does not free dir itself. + * Frees memory within dir which was allocated, and resets fields for further + * use. Does not free dir itself. */ void clear_directory(struct dir_struct *dir) { @@ -3030,6 +3030,13 @@ void clear_directory(struct dir_struct *dir) free(group->pl); } + for (i = 0; i < dir->ignored_nr; i++) + free(dir->ignored[i]); + for (i = 0; i < dir->nr; i++) + free(dir->entries[i]); + free(dir->ignored); + free(dir->entries); + stk = dir->exclude_stack; while (stk) { struct exclude_stack *prev = stk->prev; @@ -3037,6 +3044,8 @@ void clear_directory(struct dir_struct *dir) stk = prev; } strbuf_release(&dir->basebuf); + + memset(&dir, 0, sizeof(*dir)); } struct ondisk_untracked_cache { diff --git a/dir.h b/dir.h index 5855c065a6..7d76d0644f 100644 --- a/dir.h +++ b/dir.h @@ -36,7 +36,7 @@ * * - Use `dir.entries[]`. * - * - Call `clear_directory()` when none of the contained elements are no longer in use. + * - Call `clear_directory()` when the contained elements are no longer in use. * */ diff --git a/wt-status.c b/wt-status.c index d75399085d..c00ea3e06a 100644 --- a/wt-status.c +++ b/wt-status.c @@ -724,18 +724,14 @@ static void wt_status_collect_untracked(struct wt_status *s) struct dir_entry *ent = dir.entries[i]; if (index_name_is_other(istate, ent->name, ent->len)) string_list_insert(&s->untracked, ent->name); - free(ent); } for (i = 0; i < dir.ignored_nr; i++) { struct dir_entry *ent = dir.ignored[i]; if (index_name_is_other(istate, ent->name, ent->len)) string_list_insert(&s->ignored, ent->name); - free(ent); } - free(dir.entries); - free(dir.ignored); clear_directory(&dir); if (advice_status_u_option) From eceba5321410bbcc9e0b11e6aa479832f574eca8 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Tue, 18 Aug 2020 22:58:26 +0000 Subject: [PATCH 2/2] dir: fix problematic API to avoid memory leaks The dir structure seemed to have a number of leaks and problems around it. First I noticed that parent_hashmap and recursive_hashmap were being leaked (though Peff noticed and submitted fixes before me). Then I noticed in the previous commit that clear_directory() was only taking responsibility for a subset of fields within dir_struct, despite the fact that entries[] and ignored[] we allocated internally to dir.c. That, of course, resulted in many callers either leaking or haphazardly trying to free these arrays and their contents. Digging further, I found that despite the pretty clear documentation near the top of dir.h that folks were supposed to call clear_directory() when the user no longer needed the dir_struct, there were four callers that didn't bother doing that at all. However, two of them clearly thought about leaks since they had an UNLEAK(dir) directive, which to me suggests that the method to free the data was too unclear. I suspect the non-obviousness of the API and its holes led folks to avoid it, which then snowballed into further problems with the entries[], ignored[], parent_hashmap, and recursive_hashmap problems. Rename clear_directory() to dir_clear() to be more in line with other data structures in git, and introduce a dir_init() to handle the suggested memsetting of dir_struct to all zeroes. I hope that a name like "dir_clear()" is more clear, and that the presence of dir_init() will provide a hint to those looking at the code that they need to look for either a dir_clear() or a dir_free() and lead them to find dir_clear(). Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- builtin/add.c | 4 ++-- builtin/check-ignore.c | 4 ++-- builtin/clean.c | 8 ++++---- builtin/grep.c | 3 ++- builtin/ls-files.c | 4 ++-- builtin/stash.c | 4 ++-- dir.c | 9 +++++++-- dir.h | 21 +++++++++++---------- merge.c | 3 ++- wt-status.c | 4 ++-- 10 files changed, 36 insertions(+), 28 deletions(-) diff --git a/builtin/add.c b/builtin/add.c index ab39a60a0d..b36a99eb7c 100644 --- a/builtin/add.c +++ b/builtin/add.c @@ -534,11 +534,11 @@ int cmd_add(int argc, const char **argv, const char *prefix) die_in_unpopulated_submodule(&the_index, prefix); die_path_inside_submodule(&the_index, &pathspec); + dir_init(&dir); if (add_new_files) { int baselen; /* Set up the default git porcelain excludes */ - memset(&dir, 0, sizeof(dir)); if (!ignored_too) { dir.flags |= DIR_COLLECT_IGNORED; setup_standard_excludes(&dir); @@ -611,7 +611,7 @@ int cmd_add(int argc, const char **argv, const char *prefix) COMMIT_LOCK | SKIP_IF_UNCHANGED)) die(_("Unable to write new index file")); + dir_clear(&dir); UNLEAK(pathspec); - UNLEAK(dir); return exit_status; } diff --git a/builtin/check-ignore.c b/builtin/check-ignore.c index ea5d0ae3a6..3c652748d5 100644 --- a/builtin/check-ignore.c +++ b/builtin/check-ignore.c @@ -180,7 +180,7 @@ int cmd_check_ignore(int argc, const char **argv, const char *prefix) if (!no_index && read_cache() < 0) die(_("index file corrupt")); - memset(&dir, 0, sizeof(dir)); + dir_init(&dir); setup_standard_excludes(&dir); if (stdin_paths) { @@ -190,7 +190,7 @@ int cmd_check_ignore(int argc, const char **argv, const char *prefix) maybe_flush_or_die(stdout, "ignore to stdout"); } - clear_directory(&dir); + dir_clear(&dir); return !num_ignored; } diff --git a/builtin/clean.c b/builtin/clean.c index 4ffe00dd7f..e53ea52d89 100644 --- a/builtin/clean.c +++ b/builtin/clean.c @@ -667,7 +667,7 @@ static int filter_by_patterns_cmd(void) if (!confirm.len) break; - memset(&dir, 0, sizeof(dir)); + dir_init(&dir); pl = add_pattern_list(&dir, EXC_CMDL, "manual exclude"); ignore_list = strbuf_split_max(&confirm, ' ', 0); @@ -698,7 +698,7 @@ static int filter_by_patterns_cmd(void) } strbuf_list_free(ignore_list); - clear_directory(&dir); + dir_clear(&dir); } strbuf_release(&confirm); @@ -923,7 +923,7 @@ int cmd_clean(int argc, const char **argv, const char *prefix) argc = parse_options(argc, argv, prefix, options, builtin_clean_usage, 0); - memset(&dir, 0, sizeof(dir)); + dir_init(&dir); if (!interactive && !dry_run && !force) { if (config_set) die(_("clean.requireForce set to true and neither -i, -n, nor -f given; " @@ -1021,7 +1021,7 @@ int cmd_clean(int argc, const char **argv, const char *prefix) string_list_append(&del_list, rel); } - clear_directory(&dir); + dir_clear(&dir); if (interactive && del_list.nr > 0) interactive_main_loop(); diff --git a/builtin/grep.c b/builtin/grep.c index cee9db3477..f58979bc3f 100644 --- a/builtin/grep.c +++ b/builtin/grep.c @@ -693,7 +693,7 @@ static int grep_directory(struct grep_opt *opt, const struct pathspec *pathspec, struct dir_struct dir; int i, hit = 0; - memset(&dir, 0, sizeof(dir)); + dir_init(&dir); if (!use_index) dir.flags |= DIR_NO_GITLINKS; if (exc_std) @@ -705,6 +705,7 @@ static int grep_directory(struct grep_opt *opt, const struct pathspec *pathspec, if (hit && opt->status_only) break; } + dir_clear(&dir); return hit; } diff --git a/builtin/ls-files.c b/builtin/ls-files.c index 30a4c10334..c8eae899b8 100644 --- a/builtin/ls-files.c +++ b/builtin/ls-files.c @@ -584,7 +584,7 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix) if (argc == 2 && !strcmp(argv[1], "-h")) usage_with_options(ls_files_usage, builtin_ls_files_options); - memset(&dir, 0, sizeof(dir)); + dir_init(&dir); prefix = cmd_prefix; if (prefix) prefix_len = strlen(prefix); @@ -688,6 +688,6 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix) return bad ? 1 : 0; } - UNLEAK(dir); + dir_clear(&dir); return 0; } diff --git a/builtin/stash.c b/builtin/stash.c index da48533d49..4bdfaf8397 100644 --- a/builtin/stash.c +++ b/builtin/stash.c @@ -864,7 +864,7 @@ static int get_untracked_files(const struct pathspec *ps, int include_untracked, int found = 0; struct dir_struct dir; - memset(&dir, 0, sizeof(dir)); + dir_init(&dir); if (include_untracked != INCLUDE_ALL_FILES) setup_standard_excludes(&dir); @@ -877,7 +877,7 @@ static int get_untracked_files(const struct pathspec *ps, int include_untracked, strbuf_addch(untracked_files, '\0'); } - clear_directory(&dir); + dir_clear(&dir); return found; } diff --git a/dir.c b/dir.c index aa96030031..8d6c59a9dc 100644 --- a/dir.c +++ b/dir.c @@ -54,6 +54,11 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, static int resolve_dtype(int dtype, struct index_state *istate, const char *path, int len); +void dir_init(struct dir_struct *dir) +{ + memset(dir, 0, sizeof(*dir)); +} + int count_slashes(const char *s) { int cnt = 0; @@ -3012,7 +3017,7 @@ int remove_path(const char *name) * Frees memory within dir which was allocated, and resets fields for further * use. Does not free dir itself. */ -void clear_directory(struct dir_struct *dir) +void dir_clear(struct dir_struct *dir) { int i, j; struct exclude_list_group *group; @@ -3045,7 +3050,7 @@ void clear_directory(struct dir_struct *dir) } strbuf_release(&dir->basebuf); - memset(&dir, 0, sizeof(*dir)); + dir_init(dir); } struct ondisk_untracked_cache { diff --git a/dir.h b/dir.h index 7d76d0644f..a3c40dec51 100644 --- a/dir.h +++ b/dir.h @@ -19,24 +19,23 @@ * CE_SKIP_WORKTREE marked. If you want to exclude files, make sure you have * loaded the index first. * - * - Prepare `struct dir_struct dir` and clear it with `memset(&dir, 0, - * sizeof(dir))`. + * - Prepare `struct dir_struct dir` using `dir_init()` function. * * - To add single exclude pattern, call `add_pattern_list()` and then * `add_pattern()`. * * - To add patterns from a file (e.g. `.git/info/exclude`), call - * `add_patterns_from_file()` , and/or set `dir.exclude_per_dir`. A - * short-hand function `setup_standard_excludes()` can be used to set - * up the standard set of exclude settings. + * `add_patterns_from_file()` , and/or set `dir.exclude_per_dir`. * - * - Set options described in the Data Structure section above. + * - A short-hand function `setup_standard_excludes()` can be used to set + * up the standard set of exclude settings, instead of manually calling + * the add_pattern*() family of functions. * - * - Call `read_directory()`. + * - Call `fill_directory()`. * - * - Use `dir.entries[]`. + * - Use `dir.entries[]` and `dir.ignored[]`. * - * - Call `clear_directory()` when the contained elements are no longer in use. + * - Call `dir_clear()` when the contained elements are no longer in use. * */ @@ -362,6 +361,8 @@ int match_pathspec(const struct index_state *istate, int report_path_error(const char *ps_matched, const struct pathspec *pathspec); int within_depth(const char *name, int namelen, int depth, int max_depth); +void dir_init(struct dir_struct *dir); + int fill_directory(struct dir_struct *dir, struct index_state *istate, const struct pathspec *pathspec); @@ -428,7 +429,7 @@ void parse_path_pattern(const char **string, int *patternlen, unsigned *flags, i void add_pattern(const char *string, const char *base, int baselen, struct pattern_list *pl, int srcpos); void clear_pattern_list(struct pattern_list *pl); -void clear_directory(struct dir_struct *dir); +void dir_clear(struct dir_struct *dir); int repo_file_exists(struct repository *repo, const char *path); int file_exists(const char *); diff --git a/merge.c b/merge.c index 753e461659..5fb88af102 100644 --- a/merge.c +++ b/merge.c @@ -80,8 +80,8 @@ int checkout_fast_forward(struct repository *r, } memset(&opts, 0, sizeof(opts)); + dir_init(&dir); if (overwrite_ignore) { - memset(&dir, 0, sizeof(dir)); dir.flags |= DIR_SHOW_IGNORED; setup_standard_excludes(&dir); opts.dir = &dir; @@ -102,6 +102,7 @@ int checkout_fast_forward(struct repository *r, clear_unpack_trees_porcelain(&opts); return -1; } + dir_clear(&dir); clear_unpack_trees_porcelain(&opts); if (write_locked_index(r->index, &lock_file, COMMIT_LOCK)) diff --git a/wt-status.c b/wt-status.c index c00ea3e06a..7ce58b8aae 100644 --- a/wt-status.c +++ b/wt-status.c @@ -703,7 +703,7 @@ static void wt_status_collect_untracked(struct wt_status *s) if (!s->show_untracked_files) return; - memset(&dir, 0, sizeof(dir)); + dir_init(&dir); if (s->show_untracked_files != SHOW_ALL_UNTRACKED_FILES) dir.flags |= DIR_SHOW_OTHER_DIRECTORIES | DIR_HIDE_EMPTY_DIRECTORIES; @@ -732,7 +732,7 @@ static void wt_status_collect_untracked(struct wt_status *s) string_list_insert(&s->ignored, ent->name); } - clear_directory(&dir); + dir_clear(&dir); if (advice_status_u_option) s->untracked_in_ms = (getnanotime() - t_begin) / 1000000;