From 24a49cf78eef2a13bc3f7c730e236d58b5e2ebbe Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:08 +0000 Subject: [PATCH 01/13] t2021: fix platform-specific leftover cruft t2021.6 existed to test the status of a symlink that was left around by previous tests. It tried to also clean up the symlink after it was done so that subsequent tests wouldn't be tripped up by it. Unfortunately, since this test had a SYMLINK prerequisite, that made the cleanup platform dependent...and made a testcase I was trying to add to this testsuite fail (that testcase will be included in the next patch). Before we go and add new testcases, fix this cleanup by moving it into a separate test. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- t/t2021-checkout-overwrite.sh | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/t/t2021-checkout-overwrite.sh b/t/t2021-checkout-overwrite.sh index 713c3fa603..baca66e1a3 100755 --- a/t/t2021-checkout-overwrite.sh +++ b/t/t2021-checkout-overwrite.sh @@ -50,10 +50,13 @@ test_expect_success 'checkout commit with dir must not remove untracked a/b' ' test_expect_success SYMLINKS 'the symlink remained' ' - test_when_finished "rm a/b" && test -h a/b ' +test_expect_success 'cleanup after previous symlink tests' ' + rm a/b +' + test_expect_success SYMLINKS 'checkout -f must not follow symlinks when removing entries' ' git checkout -f start && mkdir dir && From b413a827126abd54fa95470be7c63fa4f00d5d47 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:09 +0000 Subject: [PATCH 02/13] unpack-trees: heed requests to overwrite ignored files When a directory exists but has only ignored files within it and we are trying to switch to a branch that has a file where that directory is, the behavior depends upon --[no]-overwrite-ignore. If the user wants to --overwrite-ignore (the default), then we should delete the ignored file and directory and switch to the new branch. The code to handle this in verify_clean_subdirectory() in unpack-trees tried to handle this via paying attention to the exclude_per_dir setting of the internal dir field. This came from commit c81935348b ("Fix switching to a branch with D/F when current branch has file D.", 2007-03-15), which pre-dated 039bc64e88 ("core.excludesfile clean-up", 2007-11-14), and thus did not pay attention to ignore patterns from other relevant files. Change it to use setup_standard_excludes() so that it is also aware of excludes specified in other locations. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- t/t2021-checkout-overwrite.sh | 11 +++++++++++ unpack-trees.c | 2 +- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/t/t2021-checkout-overwrite.sh b/t/t2021-checkout-overwrite.sh index baca66e1a3..034f62c13c 100755 --- a/t/t2021-checkout-overwrite.sh +++ b/t/t2021-checkout-overwrite.sh @@ -69,4 +69,15 @@ test_expect_success SYMLINKS 'checkout -f must not follow symlinks when removing test_path_is_file untracked/f ' +test_expect_success 'checkout --overwrite-ignore should succeed if only ignored files in the way' ' + git checkout -b df_conflict && + test_commit contents some_dir && + git checkout start && + mkdir some_dir && + echo autogenerated information >some_dir/ignore && + echo ignore >.git/info/exclude && + git checkout --overwrite-ignore df_conflict && + ! test_path_is_dir some_dir +' + test_done diff --git a/unpack-trees.c b/unpack-trees.c index 3d05e45a27..4518d33ed9 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -2337,7 +2337,7 @@ static int verify_clean_subdirectory(const struct cache_entry *ce, memset(&d, 0, sizeof(d)); if (o->dir) - d.exclude_per_dir = o->dir->exclude_per_dir; + setup_standard_excludes(&d); i = read_directory(&d, o->src_index, pathbuf, namelen+1, NULL); dir_clear(&d); free(pathbuf); From 5fdf285e6254fff4d9560f72878456f0a53e2e38 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:10 +0000 Subject: [PATCH 03/13] dir: separate public from internal portion of dir_struct In order to make it clearer to callers what portions of dir_struct are public API, and avoid errors from them setting fields that are meant as internal API, split the fields used for internal implementation reasons into a separate embedded struct. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- dir.c | 114 +++++++++++++++++++++++++++++----------------------------- dir.h | 82 ++++++++++++++++++++++-------------------- 2 files changed, 102 insertions(+), 94 deletions(-) diff --git a/dir.c b/dir.c index 4e99f0c868..7adf242026 100644 --- a/dir.c +++ b/dir.c @@ -1190,7 +1190,7 @@ struct pattern_list *add_pattern_list(struct dir_struct *dir, struct pattern_list *pl; struct exclude_list_group *group; - group = &dir->exclude_list_group[group_type]; + group = &dir->internal.exclude_list_group[group_type]; ALLOC_GROW(group->pl, group->nr + 1, group->alloc); pl = &group->pl[group->nr++]; memset(pl, 0, sizeof(*pl)); @@ -1211,7 +1211,7 @@ static void add_patterns_from_file_1(struct dir_struct *dir, const char *fname, * differently when dir->untracked is non-NULL. */ if (!dir->untracked) - dir->unmanaged_exclude_files++; + dir->internal.unmanaged_exclude_files++; pl = add_pattern_list(dir, EXC_FILE, fname); if (add_patterns(fname, "", 0, pl, NULL, 0, oid_stat) < 0) die(_("cannot use %s as an exclude file"), fname); @@ -1219,7 +1219,7 @@ static void add_patterns_from_file_1(struct dir_struct *dir, const char *fname, void add_patterns_from_file(struct dir_struct *dir, const char *fname) { - dir->unmanaged_exclude_files++; /* see validate_untracked_cache() */ + dir->internal.unmanaged_exclude_files++; /* see validate_untracked_cache() */ add_patterns_from_file_1(dir, fname, NULL); } @@ -1519,7 +1519,7 @@ static struct path_pattern *last_matching_pattern_from_lists( struct exclude_list_group *group; struct path_pattern *pattern; for (i = EXC_CMDL; i <= EXC_FILE; i++) { - group = &dir->exclude_list_group[i]; + group = &dir->internal.exclude_list_group[i]; for (j = group->nr - 1; j >= 0; j--) { pattern = last_matching_pattern_from_list( pathname, pathlen, basename, dtype_p, @@ -1545,20 +1545,20 @@ static void prep_exclude(struct dir_struct *dir, struct untracked_cache_dir *untracked; int current; - group = &dir->exclude_list_group[EXC_DIRS]; + group = &dir->internal.exclude_list_group[EXC_DIRS]; /* * Pop the exclude lists from the EXCL_DIRS exclude_list_group * which originate from directories not in the prefix of the * path being checked. */ - while ((stk = dir->exclude_stack) != NULL) { + while ((stk = dir->internal.exclude_stack) != NULL) { if (stk->baselen <= baselen && - !strncmp(dir->basebuf.buf, base, stk->baselen)) + !strncmp(dir->internal.basebuf.buf, base, stk->baselen)) break; - pl = &group->pl[dir->exclude_stack->exclude_ix]; - dir->exclude_stack = stk->prev; - dir->pattern = NULL; + pl = &group->pl[dir->internal.exclude_stack->exclude_ix]; + dir->internal.exclude_stack = stk->prev; + dir->internal.pattern = NULL; free((char *)pl->src); /* see strbuf_detach() below */ clear_pattern_list(pl); free(stk); @@ -1566,7 +1566,7 @@ static void prep_exclude(struct dir_struct *dir, } /* Skip traversing into sub directories if the parent is excluded */ - if (dir->pattern) + if (dir->internal.pattern) return; /* @@ -1574,12 +1574,12 @@ static void prep_exclude(struct dir_struct *dir, * memset(dir, 0, sizeof(*dir)) before use. Changing all of * them seems lots of work for little benefit. */ - if (!dir->basebuf.buf) - strbuf_init(&dir->basebuf, PATH_MAX); + if (!dir->internal.basebuf.buf) + strbuf_init(&dir->internal.basebuf, PATH_MAX); /* Read from the parent directories and push them down. */ current = stk ? stk->baselen : -1; - strbuf_setlen(&dir->basebuf, current < 0 ? 0 : current); + strbuf_setlen(&dir->internal.basebuf, current < 0 ? 0 : current); if (dir->untracked) untracked = stk ? stk->ucd : dir->untracked->root; else @@ -1599,32 +1599,33 @@ static void prep_exclude(struct dir_struct *dir, die("oops in prep_exclude"); cp++; untracked = - lookup_untracked(dir->untracked, untracked, + lookup_untracked(dir->untracked, + untracked, base + current, cp - base - current); } - stk->prev = dir->exclude_stack; + stk->prev = dir->internal.exclude_stack; stk->baselen = cp - base; stk->exclude_ix = group->nr; stk->ucd = untracked; pl = add_pattern_list(dir, EXC_DIRS, NULL); - strbuf_add(&dir->basebuf, base + current, stk->baselen - current); - assert(stk->baselen == dir->basebuf.len); + strbuf_add(&dir->internal.basebuf, base + current, stk->baselen - current); + assert(stk->baselen == dir->internal.basebuf.len); /* Abort if the directory is excluded */ if (stk->baselen) { int dt = DT_DIR; - dir->basebuf.buf[stk->baselen - 1] = 0; - dir->pattern = last_matching_pattern_from_lists(dir, + dir->internal.basebuf.buf[stk->baselen - 1] = 0; + dir->internal.pattern = last_matching_pattern_from_lists(dir, istate, - dir->basebuf.buf, stk->baselen - 1, - dir->basebuf.buf + current, &dt); - dir->basebuf.buf[stk->baselen - 1] = '/'; - if (dir->pattern && - dir->pattern->flags & PATTERN_FLAG_NEGATIVE) - dir->pattern = NULL; - if (dir->pattern) { - dir->exclude_stack = stk; + dir->internal.basebuf.buf, stk->baselen - 1, + dir->internal.basebuf.buf + current, &dt); + dir->internal.basebuf.buf[stk->baselen - 1] = '/'; + if (dir->internal.pattern && + dir->internal.pattern->flags & PATTERN_FLAG_NEGATIVE) + dir->internal.pattern = NULL; + if (dir->internal.pattern) { + dir->internal.exclude_stack = stk; return; } } @@ -1647,15 +1648,15 @@ static void prep_exclude(struct dir_struct *dir, */ !is_null_oid(&untracked->exclude_oid))) { /* - * dir->basebuf gets reused by the traversal, but we - * need fname to remain unchanged to ensure the src - * member of each struct path_pattern correctly + * dir->internal.basebuf gets reused by the traversal, + * but we need fname to remain unchanged to ensure the + * src member of each struct path_pattern correctly * back-references its source file. Other invocations * of add_pattern_list provide stable strings, so we * strbuf_detach() and free() here in the caller. */ struct strbuf sb = STRBUF_INIT; - strbuf_addbuf(&sb, &dir->basebuf); + strbuf_addbuf(&sb, &dir->internal.basebuf); strbuf_addstr(&sb, dir->exclude_per_dir); pl->src = strbuf_detach(&sb, NULL); add_patterns(pl->src, pl->src, stk->baselen, pl, istate, @@ -1681,10 +1682,10 @@ static void prep_exclude(struct dir_struct *dir, invalidate_gitignore(dir->untracked, untracked); oidcpy(&untracked->exclude_oid, &oid_stat.oid); } - dir->exclude_stack = stk; + dir->internal.exclude_stack = stk; current = stk->baselen; } - strbuf_setlen(&dir->basebuf, baselen); + strbuf_setlen(&dir->internal.basebuf, baselen); } /* @@ -1704,8 +1705,8 @@ struct path_pattern *last_matching_pattern(struct dir_struct *dir, prep_exclude(dir, istate, pathname, basename-pathname); - if (dir->pattern) - return dir->pattern; + if (dir->internal.pattern) + return dir->internal.pattern; return last_matching_pattern_from_lists(dir, istate, pathname, pathlen, basename, dtype_p); @@ -1742,7 +1743,7 @@ static struct dir_entry *dir_add_name(struct dir_struct *dir, if (index_file_exists(istate, pathname, len, ignore_case)) return NULL; - ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc); + ALLOC_GROW(dir->entries, dir->nr+1, dir->internal.alloc); return dir->entries[dir->nr++] = dir_entry_new(pathname, len); } @@ -1753,7 +1754,7 @@ struct dir_entry *dir_add_ignored(struct dir_struct *dir, if (!index_name_is_other(istate, pathname, len)) return NULL; - ALLOC_GROW(dir->ignored, dir->ignored_nr+1, dir->ignored_alloc); + ALLOC_GROW(dir->ignored, dir->ignored_nr+1, dir->internal.ignored_alloc); return dir->ignored[dir->ignored_nr++] = dir_entry_new(pathname, len); } @@ -2569,7 +2570,7 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, if (open_cached_dir(&cdir, dir, untracked, istate, &path, check_only)) goto out; - dir->visited_directories++; + dir->internal.visited_directories++; if (untracked) untracked->check_only = !!check_only; @@ -2578,7 +2579,7 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, /* check how the file or directory should be treated */ state = treat_path(dir, untracked, &cdir, istate, &path, baselen, pathspec); - dir->visited_paths++; + dir->internal.visited_paths++; if (state > dir_state) dir_state = state; @@ -2586,7 +2587,8 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir, /* recurse into subdir if instructed by treat_path */ if (state == path_recurse) { struct untracked_cache_dir *ud; - ud = lookup_untracked(dir->untracked, untracked, + ud = lookup_untracked(dir->untracked, + untracked, path.buf + baselen, path.len - baselen); subdir_state = @@ -2846,7 +2848,7 @@ static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *d * condition also catches running setup_standard_excludes() * before setting dir->untracked! */ - if (dir->unmanaged_exclude_files) + if (dir->internal.unmanaged_exclude_files) return NULL; /* @@ -2875,7 +2877,7 @@ static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *d * EXC_CMDL is not considered in the cache. If people set it, * skip the cache. */ - if (dir->exclude_list_group[EXC_CMDL].nr) + if (dir->internal.exclude_list_group[EXC_CMDL].nr) return NULL; if (!ident_in_untracked(dir->untracked)) { @@ -2935,15 +2937,15 @@ static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *d /* Validate $GIT_DIR/info/exclude and core.excludesfile */ root = dir->untracked->root; - if (!oideq(&dir->ss_info_exclude.oid, + if (!oideq(&dir->internal.ss_info_exclude.oid, &dir->untracked->ss_info_exclude.oid)) { invalidate_gitignore(dir->untracked, root); - dir->untracked->ss_info_exclude = dir->ss_info_exclude; + dir->untracked->ss_info_exclude = dir->internal.ss_info_exclude; } - if (!oideq(&dir->ss_excludes_file.oid, + if (!oideq(&dir->internal.ss_excludes_file.oid, &dir->untracked->ss_excludes_file.oid)) { invalidate_gitignore(dir->untracked, root); - dir->untracked->ss_excludes_file = dir->ss_excludes_file; + dir->untracked->ss_excludes_file = dir->internal.ss_excludes_file; } /* Make sure this directory is not dropped out at saving phase */ @@ -2969,9 +2971,9 @@ static void emit_traversal_statistics(struct dir_struct *dir, } trace2_data_intmax("read_directory", repo, - "directories-visited", dir->visited_directories); + "directories-visited", dir->internal.visited_directories); trace2_data_intmax("read_directory", repo, - "paths-visited", dir->visited_paths); + "paths-visited", dir->internal.visited_paths); if (!dir->untracked) return; @@ -2993,8 +2995,8 @@ int read_directory(struct dir_struct *dir, struct index_state *istate, struct untracked_cache_dir *untracked; trace2_region_enter("dir", "read_directory", istate->repo); - dir->visited_paths = 0; - dir->visited_directories = 0; + dir->internal.visited_paths = 0; + dir->internal.visited_directories = 0; if (has_symlink_leading_path(path, len)) { trace2_region_leave("dir", "read_directory", istate->repo); @@ -3342,14 +3344,14 @@ void setup_standard_excludes(struct dir_struct *dir) excludes_file = xdg_config_home("ignore"); if (excludes_file && !access_or_warn(excludes_file, R_OK, 0)) add_patterns_from_file_1(dir, excludes_file, - dir->untracked ? &dir->ss_excludes_file : NULL); + dir->untracked ? &dir->internal.ss_excludes_file : NULL); /* per repository user preference */ if (startup_info->have_repository) { const char *path = git_path_info_exclude(); if (!access_or_warn(path, R_OK, 0)) add_patterns_from_file_1(dir, path, - dir->untracked ? &dir->ss_info_exclude : NULL); + dir->untracked ? &dir->internal.ss_info_exclude : NULL); } } @@ -3405,7 +3407,7 @@ void dir_clear(struct dir_struct *dir) struct dir_struct new = DIR_INIT; for (i = EXC_CMDL; i <= EXC_FILE; i++) { - group = &dir->exclude_list_group[i]; + group = &dir->internal.exclude_list_group[i]; for (j = 0; j < group->nr; j++) { pl = &group->pl[j]; if (i == EXC_DIRS) @@ -3422,13 +3424,13 @@ void dir_clear(struct dir_struct *dir) free(dir->ignored); free(dir->entries); - stk = dir->exclude_stack; + stk = dir->internal.exclude_stack; while (stk) { struct exclude_stack *prev = stk->prev; free(stk); stk = prev; } - strbuf_release(&dir->basebuf); + strbuf_release(&dir->internal.basebuf); memcpy(dir, &new, sizeof(*dir)); } diff --git a/dir.h b/dir.h index 8acfc04418..33fd848fc8 100644 --- a/dir.h +++ b/dir.h @@ -215,14 +215,9 @@ struct dir_struct { /* The number of members in `entries[]` array. */ int nr; - /* Internal use; keeps track of allocation of `entries[]` array.*/ - int alloc; - /* The number of members in `ignored[]` array. */ int ignored_nr; - int ignored_alloc; - /* bit-field of options */ enum { @@ -296,51 +291,62 @@ struct dir_struct { */ struct dir_entry **ignored; + /* Enable/update untracked file cache if set */ + struct untracked_cache *untracked; + /** * The name of the file to be read in each directory for excluded files * (typically `.gitignore`). */ const char *exclude_per_dir; - /* - * We maintain three groups of exclude pattern lists: - * - * EXC_CMDL lists patterns explicitly given on the command line. - * EXC_DIRS lists patterns obtained from per-directory ignore files. - * EXC_FILE lists patterns from fallback ignore files, e.g. - * - .git/info/exclude - * - core.excludesfile - * - * Each group contains multiple exclude lists, a single list - * per source. - */ + struct dir_struct_internal { + /* Keeps track of allocation of `entries[]` array.*/ + int alloc; + + /* Keeps track of allocation of `ignored[]` array. */ + int ignored_alloc; + + /* + * We maintain three groups of exclude pattern lists: + * + * EXC_CMDL lists patterns explicitly given on the command line. + * EXC_DIRS lists patterns obtained from per-directory ignore + * files. + * EXC_FILE lists patterns from fallback ignore files, e.g. + * - .git/info/exclude + * - core.excludesfile + * + * Each group contains multiple exclude lists, a single list + * per source. + */ #define EXC_CMDL 0 #define EXC_DIRS 1 #define EXC_FILE 2 - struct exclude_list_group exclude_list_group[3]; + struct exclude_list_group exclude_list_group[3]; - /* - * Temporary variables which are used during loading of the - * per-directory exclude lists. - * - * exclude_stack points to the top of the exclude_stack, and - * basebuf contains the full path to the current - * (sub)directory in the traversal. Exclude points to the - * matching exclude struct if the directory is excluded. - */ - struct exclude_stack *exclude_stack; - struct path_pattern *pattern; - struct strbuf basebuf; + /* + * Temporary variables which are used during loading of the + * per-directory exclude lists. + * + * exclude_stack points to the top of the exclude_stack, and + * basebuf contains the full path to the current + * (sub)directory in the traversal. Exclude points to the + * matching exclude struct if the directory is excluded. + */ + struct exclude_stack *exclude_stack; + struct path_pattern *pattern; + struct strbuf basebuf; - /* Enable untracked file cache if set */ - struct untracked_cache *untracked; - struct oid_stat ss_info_exclude; - struct oid_stat ss_excludes_file; - unsigned unmanaged_exclude_files; + /* Additional metadata related to 'untracked' */ + struct oid_stat ss_info_exclude; + struct oid_stat ss_excludes_file; + unsigned unmanaged_exclude_files; - /* Stats about the traversal */ - unsigned visited_paths; - unsigned visited_directories; + /* Stats about the traversal */ + unsigned visited_paths; + unsigned visited_directories; + } internal; }; #define DIR_INIT { 0 } From 59e009bf15cefd89105c3e162776ccf10f4e68f1 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:11 +0000 Subject: [PATCH 04/13] dir: add a usage note to exclude_per_dir As evidenced by the fix a couple commits ago, places in the code using exclude_per_dir are likely buggy and should be adapted to call setup_standard_excludes() instead. Unfortunately, the usage of exclude_per_dir has been hardcoded into the arguments ls-files accepts, so we cannot actually remove it. Add a note that it is deprecated and no other callers should use it directly. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- dir.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/dir.h b/dir.h index 33fd848fc8..2196e12630 100644 --- a/dir.h +++ b/dir.h @@ -295,8 +295,12 @@ struct dir_struct { struct untracked_cache *untracked; /** - * The name of the file to be read in each directory for excluded files - * (typically `.gitignore`). + * Deprecated: ls-files is the only allowed caller; all other callers + * should leave this as NULL; it pre-dated the + * setup_standard_excludes() mechanism that replaces this. + * + * This field tracks the name of the file to be read in each directory + * for excluded files (typically `.gitignore`). */ const char *exclude_per_dir; From d144a9d30d883ec4b2ea5ed065e1b42237217c14 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:12 +0000 Subject: [PATCH 05/13] dir: mark output only fields of dir_struct as such While at it, also group these fields together for convenience. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- dir.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/dir.h b/dir.h index 2196e12630..e8106e1eca 100644 --- a/dir.h +++ b/dir.h @@ -212,12 +212,6 @@ struct untracked_cache { */ struct dir_struct { - /* The number of members in `entries[]` array. */ - int nr; - - /* The number of members in `ignored[]` array. */ - int ignored_nr; - /* bit-field of options */ enum { @@ -282,14 +276,20 @@ struct dir_struct { DIR_SKIP_NESTED_GIT = 1<<9 } flags; + /* The number of members in `entries[]` array. */ + int nr; /* output only */ + + /* The number of members in `ignored[]` array. */ + int ignored_nr; /* output only */ + /* An array of `struct dir_entry`, each element of which describes a path. */ - struct dir_entry **entries; + struct dir_entry **entries; /* output only */ /** * used for ignored paths with the `DIR_SHOW_IGNORED_TOO` and * `DIR_COLLECT_IGNORED` flags. */ - struct dir_entry **ignored; + struct dir_entry **ignored; /* output only */ /* Enable/update untracked file cache if set */ struct untracked_cache *untracked; From 5d4f4a592e99e8fb220b2db410f0d81203f3762e Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:13 +0000 Subject: [PATCH 06/13] unpack-trees: clean up some flow control The update_sparsity() function was introduced in commit 7af7a25853 ("unpack-trees: add a new update_sparsity() function", 2020-03-27). Prior to that, unpack_trees() was used, but that had a few bugs because the needs of the caller were different, and different enough that unpack_trees() could not easily be modified to handle both usecases. The implementation detail that update_sparsity() was written by copying unpack_trees() and then streamlining it, and then modifying it in the needed ways still shows through in that there are leftover vestiges in both functions that are no longer needed. Clean them up. In particular: * update_sparsity() allows a pattern list to be passed in, but unpack_trees() never should use a different pattern list. Add a check and a BUG() if this gets violated. * update_sparsity() has a check early on that will BUG() if o->skip_sparse_checkout is set; as such, there's no need to check for that condition again later in the code. We can simply remove the check and its corresponding goto label. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- unpack-trees.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/unpack-trees.c b/unpack-trees.c index 4518d33ed9..bad3120a76 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -1873,6 +1873,8 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options die("unpack_trees takes at most %d trees", MAX_UNPACK_TREES); if (o->dir) BUG("o->dir is for internal use only"); + if (o->pl) + BUG("o->pl is for internal use only"); trace_performance_enter(); trace2_region_enter("unpack_trees", "unpack_trees", the_repository); @@ -1899,7 +1901,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options if (!core_apply_sparse_checkout || !o->update) o->skip_sparse_checkout = 1; - if (!o->skip_sparse_checkout && !o->pl) { + if (!o->skip_sparse_checkout) { memset(&pl, 0, sizeof(pl)); free_pattern_list = 1; populate_from_existing_patterns(o, &pl); @@ -2113,8 +2115,6 @@ enum update_sparsity_result update_sparsity(struct unpack_trees_options *o) memset(&pl, 0, sizeof(pl)); free_pattern_list = 1; populate_from_existing_patterns(o, &pl); - if (o->skip_sparse_checkout) - goto skip_sparse_checkout; } /* Expand sparse directories as needed */ @@ -2142,7 +2142,6 @@ enum update_sparsity_result update_sparsity(struct unpack_trees_options *o) ret = UPDATE_SPARSITY_WARNINGS; } -skip_sparse_checkout: if (check_updates(o, o->src_index)) ret = UPDATE_SPARSITY_WORKTREE_UPDATE_FAILURES; From 1147c56ff70d5d1152601a73c9e76b9856ceebf6 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:14 +0000 Subject: [PATCH 07/13] sparse-checkout: avoid using internal API of unpack-trees struct unpack_trees_options has the following field and comment: struct pattern_list *pl; /* for internal use */ Despite the internal-use comment, commit e091228e17 ("sparse-checkout: update working directory in-process", 2019-11-21) starting setting this field from an external caller. At the time, the only way around that would have been to modify unpack_trees() to take an extra pattern_list argument, and there's a lot of callers of that function. However, when we split update_sparsity() off as a separate function, with sparse-checkout being the sole caller, the need to update other callers went away. Fix this API problem by adding a pattern_list argument to update_sparsity() and stop setting the internal o.pl field directly. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- builtin/sparse-checkout.c | 3 +-- unpack-trees.c | 18 +++++++++++------- unpack-trees.h | 3 ++- 3 files changed, 14 insertions(+), 10 deletions(-) diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c index c373815491..4b7390ce36 100644 --- a/builtin/sparse-checkout.c +++ b/builtin/sparse-checkout.c @@ -219,14 +219,13 @@ static int update_working_directory(struct pattern_list *pl) o.dst_index = r->index; index_state_init(&o.result, r); o.skip_sparse_checkout = 0; - o.pl = pl; setup_work_tree(); repo_hold_locked_index(r, &lock_file, LOCK_DIE_ON_ERROR); setup_unpack_trees_porcelain(&o, "sparse-checkout"); - result = update_sparsity(&o); + result = update_sparsity(&o, pl); clear_unpack_trees_porcelain(&o); if (result == UPDATE_SPARSITY_WARNINGS) diff --git a/unpack-trees.c b/unpack-trees.c index bad3120a76..6e4ca6fe80 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -2091,10 +2091,10 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options * * CE_NEW_SKIP_WORKTREE is used internally. */ -enum update_sparsity_result update_sparsity(struct unpack_trees_options *o) +enum update_sparsity_result update_sparsity(struct unpack_trees_options *o, + struct pattern_list *pl) { enum update_sparsity_result ret = UPDATE_SPARSITY_SUCCESS; - struct pattern_list pl; int i; unsigned old_show_all_errors; int free_pattern_list = 0; @@ -2111,11 +2111,12 @@ enum update_sparsity_result update_sparsity(struct unpack_trees_options *o) trace_performance_enter(); /* If we weren't given patterns, use the recorded ones */ - if (!o->pl) { - memset(&pl, 0, sizeof(pl)); + if (!pl) { free_pattern_list = 1; - populate_from_existing_patterns(o, &pl); + pl = xcalloc(1, sizeof(*pl)); + populate_from_existing_patterns(o, pl); } + o->pl = pl; /* Expand sparse directories as needed */ expand_index(o->src_index, o->pl); @@ -2147,8 +2148,11 @@ enum update_sparsity_result update_sparsity(struct unpack_trees_options *o) display_warning_msgs(o); o->show_all_errors = old_show_all_errors; - if (free_pattern_list) - clear_pattern_list(&pl); + if (free_pattern_list) { + clear_pattern_list(pl); + free(pl); + o->pl = NULL; + } trace_performance_leave("update_sparsity"); return ret; } diff --git a/unpack-trees.h b/unpack-trees.h index 3a7b3e5f00..f3a6e4f90e 100644 --- a/unpack-trees.h +++ b/unpack-trees.h @@ -112,7 +112,8 @@ enum update_sparsity_result { UPDATE_SPARSITY_WORKTREE_UPDATE_FAILURES = -2 }; -enum update_sparsity_result update_sparsity(struct unpack_trees_options *options); +enum update_sparsity_result update_sparsity(struct unpack_trees_options *options, + struct pattern_list *pl); int verify_uptodate(const struct cache_entry *ce, struct unpack_trees_options *o); From 33b1b4c7681703c44babdbd229cc96a3ad540569 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:15 +0000 Subject: [PATCH 08/13] sparse-checkout: avoid using internal API of unpack-trees, take 2 Commit 2f6b1eb794 ("cache API: add a "INDEX_STATE_INIT" macro/function, add release_index()", 2023-01-12) mistakenly added some initialization of a member of unpack_trees_options that was intended to be internal-only. This initialization should be done within update_sparsity() instead. Note that while o->result is mostly meant for unpack_trees() and update_sparsity() mostly operates without o->result, check_ok_to_remove() does consult it so we need to ensure it is properly initialized. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- builtin/sparse-checkout.c | 1 - unpack-trees.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c index 4b7390ce36..8d5ae6f2a6 100644 --- a/builtin/sparse-checkout.c +++ b/builtin/sparse-checkout.c @@ -217,7 +217,6 @@ static int update_working_directory(struct pattern_list *pl) o.head_idx = -1; o.src_index = r->index; o.dst_index = r->index; - index_state_init(&o.result, r); o.skip_sparse_checkout = 0; setup_work_tree(); diff --git a/unpack-trees.c b/unpack-trees.c index 6e4ca6fe80..c8dacd76c5 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -2101,6 +2101,7 @@ enum update_sparsity_result update_sparsity(struct unpack_trees_options *o, old_show_all_errors = o->show_all_errors; o->show_all_errors = 1; + index_state_init(&o->result, o->src_index->repo); /* Sanity checks */ if (!o->update || o->index_only || o->skip_sparse_checkout) From 576de3d95608df759c1f09e84f4ce1cea3c404d4 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:16 +0000 Subject: [PATCH 09/13] unpack_trees: start splitting internal fields from public API This just splits the two fields already marked as internal-only into a separate internal struct. Future commits will add more fields that were meant to be internal-only but were not explicitly marked as such to the same struct. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- unpack-trees.c | 40 ++++++++++++++++++++-------------------- unpack-trees.h | 7 +++++-- 2 files changed, 25 insertions(+), 22 deletions(-) diff --git a/unpack-trees.c b/unpack-trees.c index c8dacd76c5..ecf89d5bfe 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -1809,7 +1809,7 @@ static void populate_from_existing_patterns(struct unpack_trees_options *o, if (get_sparse_checkout_patterns(pl) < 0) o->skip_sparse_checkout = 1; else - o->pl = pl; + o->internal.pl = pl; } static void update_sparsity_for_prefix(const char *prefix, @@ -1871,10 +1871,10 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options if (len > MAX_UNPACK_TREES) die("unpack_trees takes at most %d trees", MAX_UNPACK_TREES); - if (o->dir) - BUG("o->dir is for internal use only"); - if (o->pl) - BUG("o->pl is for internal use only"); + if (o->internal.dir) + BUG("o->internal.dir is for internal use only"); + if (o->internal.pl) + BUG("o->internal.pl is for internal use only"); trace_performance_enter(); trace2_region_enter("unpack_trees", "unpack_trees", the_repository); @@ -1891,9 +1891,9 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options BUG("UNPACK_RESET_OVERWRITE_UNTRACKED incompatible with preserved ignored files"); if (!o->preserve_ignored) { - o->dir = &dir; - o->dir->flags |= DIR_SHOW_IGNORED; - setup_standard_excludes(o->dir); + o->internal.dir = &dir; + o->internal.dir->flags |= DIR_SHOW_IGNORED; + setup_standard_excludes(o->internal.dir); } if (o->prefix) @@ -1943,7 +1943,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options * Sparse checkout loop #1: set NEW_SKIP_WORKTREE on existing entries */ if (!o->skip_sparse_checkout) - mark_new_skip_worktree(o->pl, o->src_index, 0, + mark_new_skip_worktree(o->internal.pl, o->src_index, 0, CE_NEW_SKIP_WORKTREE, o->verbose_update); if (!dfc) @@ -2009,7 +2009,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options * If they will have NEW_SKIP_WORKTREE, also set CE_SKIP_WORKTREE * so apply_sparse_checkout() won't attempt to remove it from worktree */ - mark_new_skip_worktree(o->pl, &o->result, + mark_new_skip_worktree(o->internal.pl, &o->result, CE_ADDED, CE_SKIP_WORKTREE | CE_NEW_SKIP_WORKTREE, o->verbose_update); @@ -2067,9 +2067,9 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options done: if (free_pattern_list) clear_pattern_list(&pl); - if (o->dir) { - dir_clear(o->dir); - o->dir = NULL; + if (o->internal.dir) { + dir_clear(o->internal.dir); + o->internal.dir = NULL; } trace2_region_leave("unpack_trees", "unpack_trees", the_repository); trace_performance_leave("unpack_trees"); @@ -2117,14 +2117,14 @@ enum update_sparsity_result update_sparsity(struct unpack_trees_options *o, pl = xcalloc(1, sizeof(*pl)); populate_from_existing_patterns(o, pl); } - o->pl = pl; + o->internal.pl = pl; /* Expand sparse directories as needed */ - expand_index(o->src_index, o->pl); + expand_index(o->src_index, o->internal.pl); /* Set NEW_SKIP_WORKTREE on existing entries. */ mark_all_ce_unused(o->src_index); - mark_new_skip_worktree(o->pl, o->src_index, 0, + mark_new_skip_worktree(o->internal.pl, o->src_index, 0, CE_NEW_SKIP_WORKTREE, o->verbose_update); /* Then loop over entries and update/remove as needed */ @@ -2152,7 +2152,7 @@ enum update_sparsity_result update_sparsity(struct unpack_trees_options *o, if (free_pattern_list) { clear_pattern_list(pl); free(pl); - o->pl = NULL; + o->internal.pl = NULL; } trace_performance_leave("update_sparsity"); return ret; @@ -2340,7 +2340,7 @@ static int verify_clean_subdirectory(const struct cache_entry *ce, pathbuf = xstrfmt("%.*s/", namelen, ce->name); memset(&d, 0, sizeof(d)); - if (o->dir) + if (o->internal.dir) setup_standard_excludes(&d); i = read_directory(&d, o->src_index, pathbuf, namelen+1, NULL); dir_clear(&d); @@ -2395,8 +2395,8 @@ static int check_ok_to_remove(const char *name, int len, int dtype, if (ignore_case && icase_exists(o, name, len, st)) return 0; - if (o->dir && - is_excluded(o->dir, o->src_index, name, &dtype)) + if (o->internal.dir && + is_excluded(o->internal.dir, o->src_index, name, &dtype)) /* * ce->name is explicitly excluded, so it is Ok to * overwrite it. diff --git a/unpack-trees.h b/unpack-trees.h index f3a6e4f90e..5c1a9314a0 100644 --- a/unpack-trees.h +++ b/unpack-trees.h @@ -97,9 +97,12 @@ struct unpack_trees_options { struct index_state *src_index; struct index_state result; - struct pattern_list *pl; /* for internal use */ - struct dir_struct *dir; /* for internal use only */ struct checkout_metadata meta; + + struct unpack_trees_options_internal { + struct pattern_list *pl; + struct dir_struct *dir; + } internal; }; int unpack_trees(unsigned n, struct tree_desc *t, From 13e1fd6e38f17fe7fecfb6e6c30af053a3c2c420 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:17 +0000 Subject: [PATCH 10/13] unpack-trees: mark fields only used internally as internal Continue the work from the previous patch by finding additional fields which are only used internally but not yet explicitly marked as such, and include them in the internal fields struct. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- unpack-trees.c | 159 +++++++++++++++++++++++++------------------------ unpack-trees.h | 26 ++++---- 2 files changed, 95 insertions(+), 90 deletions(-) diff --git a/unpack-trees.c b/unpack-trees.c index ecf89d5bfe..dd4b55ef49 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -66,8 +66,8 @@ static const char *unpack_plumbing_errors[NB_UNPACK_TREES_WARNING_TYPES] = { }; #define ERRORMSG(o,type) \ - ( ((o) && (o)->msgs[(type)]) \ - ? ((o)->msgs[(type)]) \ + ( ((o) && (o)->internal.msgs[(type)]) \ + ? ((o)->internal.msgs[(type)]) \ : (unpack_plumbing_errors[(type)]) ) static const char *super_prefixed(const char *path, const char *super_prefix) @@ -108,10 +108,10 @@ void setup_unpack_trees_porcelain(struct unpack_trees_options *opts, const char *cmd) { int i; - const char **msgs = opts->msgs; + const char **msgs = opts->internal.msgs; const char *msg; - strvec_init(&opts->msgs_to_free); + strvec_init(&opts->internal.msgs_to_free); if (!strcmp(cmd, "checkout")) msg = advice_enabled(ADVICE_COMMIT_BEFORE_MERGE) @@ -129,7 +129,7 @@ void setup_unpack_trees_porcelain(struct unpack_trees_options *opts, "Please commit your changes or stash them before you %s.") : _("Your local changes to the following files would be overwritten by %s:\n%%s"); msgs[ERROR_WOULD_OVERWRITE] = msgs[ERROR_NOT_UPTODATE_FILE] = - strvec_pushf(&opts->msgs_to_free, msg, cmd, cmd); + strvec_pushf(&opts->internal.msgs_to_free, msg, cmd, cmd); msgs[ERROR_NOT_UPTODATE_DIR] = _("Updating the following directories would lose untracked files in them:\n%s"); @@ -153,7 +153,7 @@ void setup_unpack_trees_porcelain(struct unpack_trees_options *opts, "Please move or remove them before you %s.") : _("The following untracked working tree files would be removed by %s:\n%%s"); msgs[ERROR_WOULD_LOSE_UNTRACKED_REMOVED] = - strvec_pushf(&opts->msgs_to_free, msg, cmd, cmd); + strvec_pushf(&opts->internal.msgs_to_free, msg, cmd, cmd); if (!strcmp(cmd, "checkout")) msg = advice_enabled(ADVICE_COMMIT_BEFORE_MERGE) @@ -171,7 +171,7 @@ void setup_unpack_trees_porcelain(struct unpack_trees_options *opts, "Please move or remove them before you %s.") : _("The following untracked working tree files would be overwritten by %s:\n%%s"); msgs[ERROR_WOULD_LOSE_UNTRACKED_OVERWRITTEN] = - strvec_pushf(&opts->msgs_to_free, msg, cmd, cmd); + strvec_pushf(&opts->internal.msgs_to_free, msg, cmd, cmd); /* * Special case: ERROR_BIND_OVERLAP refers to a pair of paths, we @@ -189,16 +189,16 @@ void setup_unpack_trees_porcelain(struct unpack_trees_options *opts, msgs[WARNING_SPARSE_ORPHANED_NOT_OVERWRITTEN] = _("The following paths were already present and thus not updated despite sparse patterns:\n%s"); - opts->show_all_errors = 1; + opts->internal.show_all_errors = 1; /* rejected paths may not have a static buffer */ - for (i = 0; i < ARRAY_SIZE(opts->unpack_rejects); i++) - opts->unpack_rejects[i].strdup_strings = 1; + for (i = 0; i < ARRAY_SIZE(opts->internal.unpack_rejects); i++) + opts->internal.unpack_rejects[i].strdup_strings = 1; } void clear_unpack_trees_porcelain(struct unpack_trees_options *opts) { - strvec_clear(&opts->msgs_to_free); - memset(opts->msgs, 0, sizeof(opts->msgs)); + strvec_clear(&opts->internal.msgs_to_free); + memset(opts->internal.msgs, 0, sizeof(opts->internal.msgs)); } static int do_add_entry(struct unpack_trees_options *o, struct cache_entry *ce, @@ -210,7 +210,7 @@ static int do_add_entry(struct unpack_trees_options *o, struct cache_entry *ce, set |= CE_WT_REMOVE; ce->ce_flags = (ce->ce_flags & ~clear) | set; - return add_index_entry(&o->result, ce, + return add_index_entry(&o->internal.result, ce, ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE); } @@ -218,7 +218,7 @@ static void add_entry(struct unpack_trees_options *o, const struct cache_entry *ce, unsigned int set, unsigned int clear) { - do_add_entry(o, dup_cache_entry(ce, &o->result), set, clear); + do_add_entry(o, dup_cache_entry(ce, &o->internal.result), set, clear); } /* @@ -233,7 +233,7 @@ static int add_rejected_path(struct unpack_trees_options *o, if (o->quiet) return -1; - if (!o->show_all_errors) + if (!o->internal.show_all_errors) return error(ERRORMSG(o, e), super_prefixed(path, o->super_prefix)); @@ -241,7 +241,7 @@ static int add_rejected_path(struct unpack_trees_options *o, * Otherwise, insert in a list for future display by * display_(error|warning)_msgs() */ - string_list_append(&o->unpack_rejects[e], path); + string_list_append(&o->internal.unpack_rejects[e], path); return -1; } @@ -253,7 +253,7 @@ static void display_error_msgs(struct unpack_trees_options *o) int e; unsigned error_displayed = 0; for (e = 0; e < NB_UNPACK_TREES_ERROR_TYPES; e++) { - struct string_list *rejects = &o->unpack_rejects[e]; + struct string_list *rejects = &o->internal.unpack_rejects[e]; if (rejects->nr > 0) { int i; @@ -281,7 +281,7 @@ static void display_warning_msgs(struct unpack_trees_options *o) unsigned warning_displayed = 0; for (e = NB_UNPACK_TREES_ERROR_TYPES + 1; e < NB_UNPACK_TREES_WARNING_TYPES; e++) { - struct string_list *rejects = &o->unpack_rejects[e]; + struct string_list *rejects = &o->internal.unpack_rejects[e]; if (rejects->nr > 0) { int i; @@ -600,13 +600,14 @@ static void mark_ce_used(struct cache_entry *ce, struct unpack_trees_options *o) { ce->ce_flags |= CE_UNPACKED; - if (o->cache_bottom < o->src_index->cache_nr && - o->src_index->cache[o->cache_bottom] == ce) { - int bottom = o->cache_bottom; + if (o->internal.cache_bottom < o->src_index->cache_nr && + o->src_index->cache[o->internal.cache_bottom] == ce) { + int bottom = o->internal.cache_bottom; + while (bottom < o->src_index->cache_nr && o->src_index->cache[bottom]->ce_flags & CE_UNPACKED) bottom++; - o->cache_bottom = bottom; + o->internal.cache_bottom = bottom; } } @@ -652,7 +653,7 @@ static void mark_ce_used_same_name(struct cache_entry *ce, static struct cache_entry *next_cache_entry(struct unpack_trees_options *o) { const struct index_state *index = o->src_index; - int pos = o->cache_bottom; + int pos = o->internal.cache_bottom; while (pos < index->cache_nr) { struct cache_entry *ce = index->cache[pos]; @@ -711,7 +712,7 @@ static void restore_cache_bottom(struct traverse_info *info, int bottom) if (o->diff_index_cached) return; - o->cache_bottom = bottom; + o->internal.cache_bottom = bottom; } static int switch_cache_bottom(struct traverse_info *info) @@ -721,13 +722,13 @@ static int switch_cache_bottom(struct traverse_info *info) if (o->diff_index_cached) return 0; - ret = o->cache_bottom; + ret = o->internal.cache_bottom; pos = find_cache_pos(info->prev, info->name, info->namelen); if (pos < -1) - o->cache_bottom = -2 - pos; + o->internal.cache_bottom = -2 - pos; else if (pos < 0) - o->cache_bottom = o->src_index->cache_nr; + o->internal.cache_bottom = o->src_index->cache_nr; return ret; } @@ -873,9 +874,9 @@ static int traverse_trees_recursive(int n, unsigned long dirmask, * save and restore cache_bottom anyway to not miss * unprocessed entries before 'pos'. */ - bottom = o->cache_bottom; + bottom = o->internal.cache_bottom; ret = traverse_by_cache_tree(pos, nr_entries, n, info); - o->cache_bottom = bottom; + o->internal.cache_bottom = bottom; return ret; } @@ -1212,7 +1213,7 @@ static int unpack_single_entry(int n, unsigned long mask, * cache entry from the index aware logic. */ src[i + o->merge] = create_ce_entry(info, names + i, stage, - &o->result, o->merge, + &o->internal.result, o->merge, bit & dirmask); } @@ -1237,7 +1238,7 @@ static int unpack_single_entry(int n, unsigned long mask, static int unpack_failed(struct unpack_trees_options *o, const char *message) { - discard_index(&o->result); + discard_index(&o->internal.result); if (!o->quiet && !o->exiting_early) { if (message) return error("%s", message); @@ -1260,7 +1261,7 @@ static int find_cache_pos(struct traverse_info *info, struct index_state *index = o->src_index; int pfxlen = info->pathlen; - for (pos = o->cache_bottom; pos < index->cache_nr; pos++) { + for (pos = o->internal.cache_bottom; pos < index->cache_nr; pos++) { const struct cache_entry *ce = index->cache[pos]; const char *ce_name, *ce_slash; int cmp, ce_len; @@ -1271,8 +1272,8 @@ static int find_cache_pos(struct traverse_info *info, * we can never match it; don't check it * again. */ - if (pos == o->cache_bottom) - ++o->cache_bottom; + if (pos == o->internal.cache_bottom) + ++o->internal.cache_bottom; continue; } if (!ce_in_traverse_path(ce, info)) { @@ -1450,7 +1451,7 @@ static int unpack_sparse_callback(int n, unsigned long mask, unsigned long dirma */ if (!is_null_oid(&names[0].oid)) { src[0] = create_ce_entry(info, &names[0], 0, - &o->result, 1, + &o->internal.result, 1, dirmask & (1ul << 0)); src[0]->ce_flags |= (CE_SKIP_WORKTREE | CE_NEW_SKIP_WORKTREE); } @@ -1560,7 +1561,7 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str * in 'mark_ce_used()' */ if (!src[0] || !S_ISSPARSEDIR(src[0]->ce_mode)) - o->cache_bottom += matches; + o->internal.cache_bottom += matches; return mask; } } @@ -1907,37 +1908,37 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options populate_from_existing_patterns(o, &pl); } - index_state_init(&o->result, o->src_index->repo); - o->result.initialized = 1; - o->result.timestamp.sec = o->src_index->timestamp.sec; - o->result.timestamp.nsec = o->src_index->timestamp.nsec; - o->result.version = o->src_index->version; + index_state_init(&o->internal.result, o->src_index->repo); + o->internal.result.initialized = 1; + o->internal.result.timestamp.sec = o->src_index->timestamp.sec; + o->internal.result.timestamp.nsec = o->src_index->timestamp.nsec; + o->internal.result.version = o->src_index->version; if (!o->src_index->split_index) { - o->result.split_index = NULL; + o->internal.result.split_index = NULL; } else if (o->src_index == o->dst_index) { /* * o->dst_index (and thus o->src_index) will be discarded - * and overwritten with o->result at the end of this function, + * and overwritten with o->internal.result at the end of this function, * so just use src_index's split_index to avoid having to * create a new one. */ - o->result.split_index = o->src_index->split_index; - o->result.split_index->refcount++; + o->internal.result.split_index = o->src_index->split_index; + o->internal.result.split_index->refcount++; } else { - o->result.split_index = init_split_index(&o->result); + o->internal.result.split_index = init_split_index(&o->internal.result); } - oidcpy(&o->result.oid, &o->src_index->oid); + oidcpy(&o->internal.result.oid, &o->src_index->oid); o->merge_size = len; mark_all_ce_unused(o->src_index); - o->result.fsmonitor_last_update = + o->internal.result.fsmonitor_last_update = xstrdup_or_null(o->src_index->fsmonitor_last_update); - o->result.fsmonitor_has_run_once = o->src_index->fsmonitor_has_run_once; + o->internal.result.fsmonitor_has_run_once = o->src_index->fsmonitor_has_run_once; if (!o->src_index->initialized && !repo->settings.command_requires_full_index && - is_sparse_index_allowed(&o->result, 0)) - o->result.sparse_index = 1; + is_sparse_index_allowed(&o->internal.result, 0)) + o->internal.result.sparse_index = 1; /* * Sparse checkout loop #1: set NEW_SKIP_WORKTREE on existing entries @@ -1957,7 +1958,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options setup_traverse_info(&info, prefix); info.fn = unpack_callback; info.data = o; - info.show_all_errors = o->show_all_errors; + info.show_all_errors = o->internal.show_all_errors; info.pathspec = o->pathspec; if (o->prefix) { @@ -1998,7 +1999,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options } mark_all_ce_unused(o->src_index); - if (o->trivial_merges_only && o->nontrivial_merge) { + if (o->trivial_merges_only && o->internal.nontrivial_merge) { ret = unpack_failed(o, "Merge requires file-level merging"); goto done; } @@ -2009,13 +2010,13 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options * If they will have NEW_SKIP_WORKTREE, also set CE_SKIP_WORKTREE * so apply_sparse_checkout() won't attempt to remove it from worktree */ - mark_new_skip_worktree(o->internal.pl, &o->result, + mark_new_skip_worktree(o->internal.pl, &o->internal.result, CE_ADDED, CE_SKIP_WORKTREE | CE_NEW_SKIP_WORKTREE, o->verbose_update); ret = 0; - for (i = 0; i < o->result.cache_nr; i++) { - struct cache_entry *ce = o->result.cache[i]; + for (i = 0; i < o->internal.result.cache_nr; i++) { + struct cache_entry *ce = o->internal.result.cache[i]; /* * Entries marked with CE_ADDED in merged_entry() do not have @@ -2029,7 +2030,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options verify_absent(ce, WARNING_SPARSE_ORPHANED_NOT_OVERWRITTEN, o)) ret = 1; - if (apply_sparse_checkout(&o->result, ce, o)) + if (apply_sparse_checkout(&o->internal.result, ce, o)) ret = 1; } if (ret == 1) { @@ -2037,30 +2038,30 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options * Inability to sparsify or de-sparsify individual * paths is not an error, but just a warning. */ - if (o->show_all_errors) + if (o->internal.show_all_errors) display_warning_msgs(o); ret = 0; } } - ret = check_updates(o, &o->result) ? (-2) : 0; + ret = check_updates(o, &o->internal.result) ? (-2) : 0; if (o->dst_index) { - move_index_extensions(&o->result, o->src_index); + move_index_extensions(&o->internal.result, o->src_index); if (!ret) { if (git_env_bool("GIT_TEST_CHECK_CACHE_TREE", 0)) - cache_tree_verify(the_repository, &o->result); + cache_tree_verify(the_repository, &o->internal.result); if (!o->skip_cache_tree_update && - !cache_tree_fully_valid(o->result.cache_tree)) - cache_tree_update(&o->result, + !cache_tree_fully_valid(o->internal.result.cache_tree)) + cache_tree_update(&o->internal.result, WRITE_TREE_SILENT | WRITE_TREE_REPAIR); } - o->result.updated_workdir = 1; + o->internal.result.updated_workdir = 1; discard_index(o->dst_index); - *o->dst_index = o->result; + *o->dst_index = o->internal.result; } else { - discard_index(&o->result); + discard_index(&o->internal.result); } o->src_index = NULL; @@ -2076,7 +2077,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options return ret; return_failed: - if (o->show_all_errors) + if (o->internal.show_all_errors) display_error_msgs(o); mark_all_ce_unused(o->src_index); ret = unpack_failed(o, NULL); @@ -2099,9 +2100,9 @@ enum update_sparsity_result update_sparsity(struct unpack_trees_options *o, unsigned old_show_all_errors; int free_pattern_list = 0; - old_show_all_errors = o->show_all_errors; - o->show_all_errors = 1; - index_state_init(&o->result, o->src_index->repo); + old_show_all_errors = o->internal.show_all_errors; + o->internal.show_all_errors = 1; + index_state_init(&o->internal.result, o->src_index->repo); /* Sanity checks */ if (!o->update || o->index_only || o->skip_sparse_checkout) @@ -2148,7 +2149,7 @@ enum update_sparsity_result update_sparsity(struct unpack_trees_options *o, ret = UPDATE_SPARSITY_WORKTREE_UPDATE_FAILURES; display_warning_msgs(o); - o->show_all_errors = old_show_all_errors; + o->internal.show_all_errors = old_show_all_errors; if (free_pattern_list) { clear_pattern_list(pl); free(pl); @@ -2248,15 +2249,15 @@ static int verify_uptodate_sparse(const struct cache_entry *ce, } /* - * TODO: We should actually invalidate o->result, not src_index [1]. + * TODO: We should actually invalidate o->internal.result, not src_index [1]. * But since cache tree and untracked cache both are not copied to - * o->result until unpacking is complete, we invalidate them on + * o->internal.result until unpacking is complete, we invalidate them on * src_index instead with the assumption that they will be copied to * dst_index at the end. * * [1] src_index->cache_tree is also used in unpack_callback() so if - * we invalidate o->result, we need to update it to use - * o->result.cache_tree as well. + * we invalidate o->internal.result, we need to update it to use + * o->internal.result.cache_tree as well. */ static void invalidate_ce_path(const struct cache_entry *ce, struct unpack_trees_options *o) @@ -2424,7 +2425,7 @@ static int check_ok_to_remove(const char *name, int len, int dtype, * delete this path, which is in a subdirectory that * is being replaced with a blob. */ - result = index_file_exists(&o->result, name, len, 0); + result = index_file_exists(&o->internal.result, name, len, 0); if (result) { if (result->ce_flags & CE_REMOVE) return 0; @@ -2525,7 +2526,7 @@ static int merged_entry(const struct cache_entry *ce, struct unpack_trees_options *o) { int update = CE_UPDATE; - struct cache_entry *merge = dup_cache_entry(ce, &o->result); + struct cache_entry *merge = dup_cache_entry(ce, &o->internal.result); if (!old) { /* @@ -2620,7 +2621,7 @@ static int merged_sparse_dir(const struct cache_entry * const *src, int n, setup_traverse_info(&info, src[0]->name); info.fn = unpack_sparse_callback; info.data = o; - info.show_all_errors = o->show_all_errors; + info.show_all_errors = o->internal.show_all_errors; info.pathspec = o->pathspec; /* Get the tree descriptors of the sparse directory in each of the merging trees */ @@ -2838,7 +2839,7 @@ int threeway_merge(const struct cache_entry * const *stages, return -1; } - o->nontrivial_merge = 1; + o->internal.nontrivial_merge = 1; /* #2, #3, #4, #6, #7, #9, #10, #11. */ count = 0; diff --git a/unpack-trees.h b/unpack-trees.h index 5c1a9314a0..0335c89bc7 100644 --- a/unpack-trees.h +++ b/unpack-trees.h @@ -59,7 +59,6 @@ struct unpack_trees_options { preserve_ignored, clone, index_only, - nontrivial_merge, trivial_merges_only, verbose_update, aggressive, @@ -70,22 +69,13 @@ struct unpack_trees_options { skip_sparse_checkout, quiet, exiting_early, - show_all_errors, dry_run, skip_cache_tree_update; enum unpack_trees_reset_type reset; const char *prefix; const char *super_prefix; - int cache_bottom; struct pathspec *pathspec; merge_fn_t fn; - const char *msgs[NB_UNPACK_TREES_WARNING_TYPES]; - struct strvec msgs_to_free; - /* - * Store error messages in an array, each case - * corresponding to a error message type - */ - struct string_list unpack_rejects[NB_UNPACK_TREES_WARNING_TYPES]; int head_idx; int merge_size; @@ -95,11 +85,25 @@ struct unpack_trees_options { struct index_state *dst_index; struct index_state *src_index; - struct index_state result; struct checkout_metadata meta; struct unpack_trees_options_internal { + unsigned int nontrivial_merge, + show_all_errors; + + int cache_bottom; + const char *msgs[NB_UNPACK_TREES_WARNING_TYPES]; + struct strvec msgs_to_free; + + /* + * Store error messages in an array, each case + * corresponding to a error message type + */ + struct string_list unpack_rejects[NB_UNPACK_TREES_WARNING_TYPES]; + + struct index_state result; + struct pattern_list *pl; struct dir_struct *dir; } internal; From 0d680a7158b647ced6a4e24a8687decc2ad6fb78 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:18 +0000 Subject: [PATCH 11/13] unpack-trees: rewrap a few overlong lines from previous patch The previous patch made many lines a little longer, resulting in four becoming a bit too long. They were left as-is for the previous patch to facilitate reviewers verifying that we were just adding "internal." in a bunch of places, but rewrap them now. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- unpack-trees.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/unpack-trees.c b/unpack-trees.c index dd4b55ef49..cac5dd0da3 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -1213,8 +1213,8 @@ static int unpack_single_entry(int n, unsigned long mask, * cache entry from the index aware logic. */ src[i + o->merge] = create_ce_entry(info, names + i, stage, - &o->internal.result, o->merge, - bit & dirmask); + &o->internal.result, + o->merge, bit & dirmask); } if (o->merge) { @@ -1918,14 +1918,15 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options } else if (o->src_index == o->dst_index) { /* * o->dst_index (and thus o->src_index) will be discarded - * and overwritten with o->internal.result at the end of this function, - * so just use src_index's split_index to avoid having to - * create a new one. + * and overwritten with o->internal.result at the end of + * this function, so just use src_index's split_index to + * avoid having to create a new one. */ o->internal.result.split_index = o->src_index->split_index; o->internal.result.split_index->refcount++; } else { - o->internal.result.split_index = init_split_index(&o->internal.result); + o->internal.result.split_index = + init_split_index(&o->internal.result); } oidcpy(&o->internal.result.oid, &o->src_index->oid); o->merge_size = len; @@ -2049,7 +2050,8 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options move_index_extensions(&o->internal.result, o->src_index); if (!ret) { if (git_env_bool("GIT_TEST_CHECK_CACHE_TREE", 0)) - cache_tree_verify(the_repository, &o->internal.result); + cache_tree_verify(the_repository, + &o->internal.result); if (!o->skip_cache_tree_update && !cache_tree_fully_valid(o->internal.result.cache_tree)) cache_tree_update(&o->internal.result, From 1ca13dd3ca6e153a2bc5b0b53555996cdd668e93 Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:19 +0000 Subject: [PATCH 12/13] unpack-trees: special case read-tree debugging as internal usage builtin/read-tree.c has some special functionality explicitly designed for debugging unpack-trees.[ch]. Associated with that is two fields that no other external caller would or should use. Mark these as internal to unpack-trees, but allow builtin/read-tree to read or write them for this special case. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- builtin/read-tree.c | 10 +++++----- unpack-trees.c | 22 +++++++++++----------- unpack-trees.h | 6 +++--- 3 files changed, 19 insertions(+), 19 deletions(-) diff --git a/builtin/read-tree.c b/builtin/read-tree.c index 3ce7541783..6034408d48 100644 --- a/builtin/read-tree.c +++ b/builtin/read-tree.c @@ -87,9 +87,9 @@ static int debug_merge(const struct cache_entry * const *stages, { int i; - printf("* %d-way merge\n", o->merge_size); + printf("* %d-way merge\n", o->internal.merge_size); debug_stage("index", stages[0], o); - for (i = 1; i <= o->merge_size; i++) { + for (i = 1; i <= o->internal.merge_size; i++) { char buf[24]; xsnprintf(buf, sizeof(buf), "ent#%d", i); debug_stage(buf, stages[i], o); @@ -144,7 +144,7 @@ int cmd_read_tree(int argc, const char **argv, const char *cmd_prefix) OPT__DRY_RUN(&opts.dry_run, N_("don't update the index or the work tree")), OPT_BOOL(0, "no-sparse-checkout", &opts.skip_sparse_checkout, N_("skip applying sparse checkout filter")), - OPT_BOOL(0, "debug-unpack", &opts.debug_unpack, + OPT_BOOL(0, "debug-unpack", &opts.internal.debug_unpack, N_("debug unpack-trees")), OPT_CALLBACK_F(0, "recurse-submodules", NULL, "checkout", "control recursive updating of submodules", @@ -247,7 +247,7 @@ int cmd_read_tree(int argc, const char **argv, const char *cmd_prefix) opts.head_idx = 1; } - if (opts.debug_unpack) + if (opts.internal.debug_unpack) opts.fn = debug_merge; /* If we're going to prime_cache_tree later, skip cache tree update */ @@ -263,7 +263,7 @@ int cmd_read_tree(int argc, const char **argv, const char *cmd_prefix) if (unpack_trees(nr_trees, t, &opts)) return 128; - if (opts.debug_unpack || opts.dry_run) + if (opts.internal.debug_unpack || opts.dry_run) return 0; /* do not write the index out */ /* diff --git a/unpack-trees.c b/unpack-trees.c index cac5dd0da3..3e5f4bd235 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -839,7 +839,7 @@ static int traverse_by_cache_tree(int pos, int nr_entries, int nr_names, mark_ce_used(src[0], o); } free(tree_ce); - if (o->debug_unpack) + if (o->internal.debug_unpack) printf("Unpacked %d entries from %s to %s using cache-tree\n", nr_entries, o->src_index->cache[pos]->name, @@ -1488,7 +1488,7 @@ static int unpack_callback(int n, unsigned long mask, unsigned long dirmask, str while (!p->mode) p++; - if (o->debug_unpack) + if (o->internal.debug_unpack) debug_unpack_callback(n, mask, dirmask, names, info); /* Are we supposed to look at the index too? */ @@ -1929,7 +1929,7 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options init_split_index(&o->internal.result); } oidcpy(&o->internal.result.oid, &o->src_index->oid); - o->merge_size = len; + o->internal.merge_size = len; mark_all_ce_unused(o->src_index); o->internal.result.fsmonitor_last_update = @@ -2882,9 +2882,9 @@ int twoway_merge(const struct cache_entry * const *src, const struct cache_entry *oldtree = src[1]; const struct cache_entry *newtree = src[2]; - if (o->merge_size != 2) + if (o->internal.merge_size != 2) return error("Cannot do a twoway merge of %d trees", - o->merge_size); + o->internal.merge_size); if (oldtree == o->df_conflict_entry) oldtree = NULL; @@ -2964,9 +2964,9 @@ int bind_merge(const struct cache_entry * const *src, const struct cache_entry *old = src[0]; const struct cache_entry *a = src[1]; - if (o->merge_size != 1) + if (o->internal.merge_size != 1) return error("Cannot do a bind merge of %d trees", - o->merge_size); + o->internal.merge_size); if (a && old) return o->quiet ? -1 : error(ERRORMSG(o, ERROR_BIND_OVERLAP), @@ -2990,9 +2990,9 @@ int oneway_merge(const struct cache_entry * const *src, const struct cache_entry *old = src[0]; const struct cache_entry *a = src[1]; - if (o->merge_size != 1) + if (o->internal.merge_size != 1) return error("Cannot do a oneway merge of %d trees", - o->merge_size); + o->internal.merge_size); if (!a || a == o->df_conflict_entry) return deleted_entry(old, old, o); @@ -3027,8 +3027,8 @@ int stash_worktree_untracked_merge(const struct cache_entry * const *src, const struct cache_entry *worktree = src[1]; const struct cache_entry *untracked = src[2]; - if (o->merge_size != 2) - BUG("invalid merge_size: %d", o->merge_size); + if (o->internal.merge_size != 2) + BUG("invalid merge_size: %d", o->internal.merge_size); if (worktree && untracked) return error(_("worktree and untracked commit have duplicate entries: %s"), diff --git a/unpack-trees.h b/unpack-trees.h index 0335c89bc7..e8737adfed 100644 --- a/unpack-trees.h +++ b/unpack-trees.h @@ -65,7 +65,6 @@ struct unpack_trees_options { skip_unmerged, initial_checkout, diff_index_cached, - debug_unpack, skip_sparse_checkout, quiet, exiting_early, @@ -78,7 +77,6 @@ struct unpack_trees_options { merge_fn_t fn; int head_idx; - int merge_size; struct cache_entry *df_conflict_entry; void *unpack_data; @@ -90,8 +88,10 @@ struct unpack_trees_options { struct unpack_trees_options_internal { unsigned int nontrivial_merge, - show_all_errors; + show_all_errors, + debug_unpack; /* used by read-tree debugging */ + int merge_size; /* used by read-tree debugging */ int cache_bottom; const char *msgs[NB_UNPACK_TREES_WARNING_TYPES]; struct strvec msgs_to_free; From f297424a3a02b552865798ac8367cf657ef1df2d Mon Sep 17 00:00:00 2001 From: Elijah Newren Date: Mon, 27 Feb 2023 15:28:20 +0000 Subject: [PATCH 13/13] unpack-trees: add usage notices around df_conflict_entry Avoid making users believe they need to initialize df_conflict_entry to something (as happened with other output only fields before) with a quick comment and a small sanity check. Signed-off-by: Elijah Newren Signed-off-by: Junio C Hamano --- unpack-trees.c | 2 ++ unpack-trees.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/unpack-trees.c b/unpack-trees.c index 3e5f4bd235..a37ab292bb 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -1876,6 +1876,8 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options BUG("o->internal.dir is for internal use only"); if (o->internal.pl) BUG("o->internal.pl is for internal use only"); + if (o->df_conflict_entry) + BUG("o->df_conflict_entry is an output only field"); trace_performance_enter(); trace2_region_enter("unpack_trees", "unpack_trees", the_repository); diff --git a/unpack-trees.h b/unpack-trees.h index e8737adfed..61c06eb7c5 100644 --- a/unpack-trees.h +++ b/unpack-trees.h @@ -78,7 +78,7 @@ struct unpack_trees_options { int head_idx; - struct cache_entry *df_conflict_entry; + struct cache_entry *df_conflict_entry; /* output only */ void *unpack_data; struct index_state *dst_index;