[PATCH v5 0/9] Directory traversal fixes

["Elijah Newren via GitGitGadget" <gitgitgadget@gmail.com>]

This patchset fixes a few directory traversal issues, where fill_directory()
would traverse into directories that it shouldn't and not traverse into
directories that it should (one of which was originally reported on this
list at [1]). And it includes a few cleanups

Changes since v4:

 * Tweak the trace2 statistics emitting a bit, as per suggestions from Jeff.
 * Introduce a new readdir_skip_dot_and_dotdot() helper at the end of the
   series, and use it everywhere we repeat the same code to skip '.' and
   '..' entries from readdir. Also use it in dir.c's read_cached_dir() so we
   can be consistent about skipping it, even for statistics, across
   platforms.

If anyone has any ideas about a better place to put the "Some sidenotes"
from the sixth commit message rather than keeping them in a random commit
message, that might be helpful.

[1] See
https://lore.kernel.org/git/DM6PR00MB06829EC5B85E0C5AC595004E894E9@DM6PR00MB0682.namprd00.prod.outlook.com/
or alternatively https://github.com/git-for-windows/git/issues/2732.

Derrick Stolee (1):
  dir: update stale description of treat_directory()

Elijah Newren (8):
  dir: convert trace calls to trace2 equivalents
  dir: report number of visited directories and paths with trace2
  ls-files: error out on -i unless -o or -c are specified
  t7300: add testcase showing unnecessary traversal into ignored
    directory
  t3001, t7300: add testcase showcasing missed directory traversal
  dir: avoid unnecessary traversal into ignored directory
  dir: traverse into untracked directories if they may have ignored
    subfiles
  dir: introduce readdir_skip_dot_and_dotdot() helper

 builtin/clean.c                    |   4 +-
 builtin/ls-files.c                 |   3 +
 builtin/worktree.c                 |   4 +-
 diff-no-index.c                    |   5 +-
 dir.c                              | 146 +++++++++++++-------
 dir.h                              |   6 +
 entry.c                            |   5 +-
 notes-merge.c                      |   5 +-
 object-file.c                      |   4 +-
 packfile.c                         |   5 +-
 rerere.c                           |   4 +-
 t/t1306-xdg-files.sh               |   2 +-
 t/t3001-ls-files-others-exclude.sh |   5 +
 t/t3003-ls-files-exclude.sh        |   4 +-
 t/t7063-status-untracked-cache.sh  | 206 +++++++++++++++++------------
 t/t7300-clean.sh                   |  42 ++++++
 t/t7519-status-fsmonitor.sh        |   8 +-
 worktree.c                         |  12 +-
 18 files changed, 298 insertions(+), 172 deletions(-)


base-commit: 311531c9de557d25ac087c1637818bd2aad6eb3a
Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-git-1020%2Fnewren%2Fdirectory-traversal-fixes-v5
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-git-1020/newren/directory-traversal-fixes-v5
Pull-Request: https://github.com/git/git/pull/1020

Range-diff vs v4:

  1:  9204e36b7e90 !  1:  6b1b4820dd20 dir: convert trace calls to trace2 equivalents
     @@ dir.c: static struct untracked_cache_dir *validate_untracked_cache(struct dir_st
       	return root;
       }
       
     -+static void trace2_read_directory_statistics(struct dir_struct *dir,
     -+					     struct repository *repo,
     -+					     const char *path)
     ++static void emit_traversal_statistics(struct dir_struct *dir,
     ++				      struct repository *repo,
     ++				      const char *path,
     ++				      int path_len)
      +{
     ++	if (!trace2_is_enabled())
     ++		return;
     ++
     ++	if (!path_len) {
     ++		trace2_data_string("read_directory", repo, "path", "");
     ++	} else {
     ++		struct strbuf tmp = STRBUF_INIT;
     ++		strbuf_add(&tmp, path, path_len);
     ++		trace2_data_string("read_directory", repo, "path", tmp.buf);
     ++		strbuf_release(&tmp);
     ++	}
     ++
      +	if (!dir->untracked)
      +		return;
     -+	trace2_data_string("read_directory", repo, "path", path);
      +	trace2_data_intmax("read_directory", repo,
      +			   "node-creation", dir->untracked->dir_created);
      +	trace2_data_intmax("read_directory", repo,
     @@ dir.c: int read_directory(struct dir_struct *dir, struct index_state *istate,
       	QSORT(dir->ignored, dir->ignored_nr, cmp_dir_entry);
       
      -	trace_performance_leave("read directory %.*s", len, path);
     -+	if (trace2_is_enabled()) {
     -+		struct strbuf tmp = STRBUF_INIT;
     -+		strbuf_add(&tmp, path, len);
     -+		trace2_read_directory_statistics(dir, istate->repo, tmp.buf);
     -+		strbuf_release(&tmp);
     -+	}
     ++	emit_traversal_statistics(dir, istate->repo, path, len);
      +
      +	trace2_region_leave("dir", "read_directory", istate->repo);
       	if (dir->untracked) {
  2:  6939253be825 !  2:  cfe2898b7a7e dir: report number of visited directories and paths with trace2
     @@ dir.c: static enum path_treatment read_directory_recursive(struct dir_struct *di
       
       		if (state > dir_state)
       			dir_state = state;
     -@@ dir.c: static void trace2_read_directory_statistics(struct dir_struct *dir,
     - 					     struct repository *repo,
     - 					     const char *path)
     - {
     +@@ dir.c: static void emit_traversal_statistics(struct dir_struct *dir,
     + 		strbuf_release(&tmp);
     + 	}
     + 
      +	trace2_data_intmax("read_directory", repo,
      +			   "directories-visited", dir->visited_directories);
      +	trace2_data_intmax("read_directory", repo,
      +			   "paths-visited", dir->visited_paths);
     ++
       	if (!dir->untracked)
       		return;
     - 	trace2_data_string("read_directory", repo, "path", path);
     + 	trace2_data_intmax("read_directory", repo,
      @@ dir.c: int read_directory(struct dir_struct *dir, struct index_state *istate,
       	struct untracked_cache_dir *untracked;
       
  3:  8d0ca8104be6 =  3:  279ef30ffbc2 ls-files: error out on -i unless -o or -c are specified
  4:  317abab3571e =  4:  5a8807a1992c t7300: add testcase showing unnecessary traversal into ignored directory
  5:  5eb019327b57 =  5:  b014ccbbaf3e t3001, t7300: add testcase showcasing missed directory traversal
  6:  89cc01ef8598 =  6:  ae1c9e37b21b dir: avoid unnecessary traversal into ignored directory
  7:  4a561e1229e4 =  7:  6fa1e85edf2f dir: traverse into untracked directories if they may have ignored subfiles
  8:  2945e749f5e3 =  8:  179f992edc92 dir: update stale description of treat_directory()
  -:  ------------ >  9:  b7c6176560bd dir: introduce readdir_skip_dot_and_dotdot() helper

-- 
gitgitgadget