Re: [PATCH v3 14/14] fsmonitor: support case-insensitive events

> From: Jeff Hostetler <jeffhostetler@github.com>
> 
> Teach fsmonitor_refresh_callback() to handle case-insensitive
> lookups if case-sensitive lookups fail on case-insensitive systems.
> This can cause 'git status' to report stale status for files if there
> are case issues/errors in the worktree.
> 
> The FSMonitor daemon sends FSEvents using the observed spelling
> of each pathname.  On case-insensitive file systems this may be
> different than the expected case spelling.
> 
> The existing code uses index_name_pos() to find the cache-entry for
> the pathname in the FSEvent and clear the CE_FSMONITOR_VALID bit so
> that the worktree scan/index refresh will revisit and revalidate the
> path.
> 
> On a case-insensitive file system, the exact match lookup may fail
> to find the associated cache-entry. This causes status to think that
> the cached CE flags are correct and skip over the file.
> 
> Update event handling to optionally use the name-hash and dir-name-hash
> if necessary.
> 
> Also update t7527 to convert the "test_expect_failure" to "_success"
> now that we have fixed the bug.
> 
> Signed-off-by: Jeff Hostetler <jeffhostetler@github.com>
> ---
>  fsmonitor.c                  | 121 +++++++++++++++++++++++++++++++++++
>  t/t7527-builtin-fsmonitor.sh |  26 +++++---
>  2 files changed, 137 insertions(+), 10 deletions(-)
> 
> diff --git a/fsmonitor.c b/fsmonitor.c
> index 3c87449be87..2b17d60bbbe 100644
> --- a/fsmonitor.c
> +++ b/fsmonitor.c
> @@ -5,6 +5,7 @@
>  #include "ewah/ewok.h"
>  #include "fsmonitor.h"
>  #include "fsmonitor-ipc.h"
> +#include "name-hash.h"
>  #include "run-command.h"
>  #include "strbuf.h"
>  #include "trace2.h"
> @@ -202,6 +203,113 @@ static void invalidate_ce_fsm(struct cache_entry *ce)
>  static size_t handle_path_with_trailing_slash(
>  	struct index_state *istate, const char *name, int pos);
>  
> +/*
> + * Use the name-hash to do a case-insensitive cache-entry lookup with
> + * the pathname and invalidate the cache-entry.
> + *
> + * Returns the number of cache-entries that we invalidated.
> + */
> +static size_t handle_using_name_hash_icase(
> +	struct index_state *istate, const char *name)
> +{
> +	struct cache_entry *ce = NULL;
> +
> +	ce = index_file_exists(istate, name, strlen(name), 1);
> +	if (!ce)
> +		return 0;
> +
> +	/*
> +	 * A case-insensitive search in the name-hash using the
> +	 * observed pathname found a cache-entry, so the observed path
> +	 * is case-incorrect.  Invalidate the cache-entry and use the
> +	 * correct spelling from the cache-entry to invalidate the
> +	 * untracked-cache.  Since we now have sparse-directories in
> +	 * the index, the observed pathname may represent a regular
> +	 * file or a sparse-index directory.
> +	 *
> +	 * Note that we should not have seen FSEvents for a
> +	 * sparse-index directory, but we handle it just in case.
> +	 *
> +	 * Either way, we know that there are not any cache-entries for
> +	 * children inside the cone of the directory, so we don't need to
> +	 * do the usual scan.
> +	 */
> +	trace_printf_key(&trace_fsmonitor,
> +			 "fsmonitor_refresh_callback MAP: '%s' '%s'",
> +			 name, ce->name);
> +
> +	/*
> +	 * NEEDSWORK: We used the name-hash to find the correct
> +	 * case-spelling of the pathname in the cache-entry[], so
> +	 * technically this is a tracked file or a sparse-directory.
> +	 * It should not have any entries in the untracked-cache, so
> +	 * we should not need to use the case-corrected spelling to
> +	 * invalidate the the untracked-cache.  So we may not need to
> +	 * do this.  For now, I'm going to be conservative and always
> +	 * do it; we can revisit this later.
> +	 */
> +	untracked_cache_invalidate_trimmed_path(istate, ce->name, 0);
> +
> +	invalidate_ce_fsm(ce);
> +	return 1;
> +}
> +
> +/*
> + * Use the dir-name-hash to find the correct-case spelling of the
> + * directory.  Use the canonical spelling to invalidate all of the
> + * cache-entries within the matching cone.
> + *
> + * Returns the number of cache-entries that we invalidated.
> + */
> +static size_t handle_using_dir_name_hash_icase(
> +	struct index_state *istate, const char *name)
> +{
> +	struct strbuf canonical_path = STRBUF_INIT;
> +	int pos;
> +	size_t len = strlen(name);
> +	size_t nr_in_cone;
> +
> +	if (name[len - 1] == '/')
> +		len--;

> +
> +	if (!index_dir_find(istate, name, len, &canonical_path))
> +		return 0; /* name is untracked */
> +
> +	if (!memcmp(name, canonical_path.buf, canonical_path.len)) {
> +		strbuf_release(&canonical_path);
> +		/*
> +		 * NEEDSWORK: Our caller already tried an exact match
> +		 * and failed to find one.  They called us to do an
> +		 * ICASE match, so we should never get an exact match,
> +		 * so we could promote this to a BUG() here if we
> +		 * wanted to.  It doesn't hurt anything to just return

> +		 * 0 and go on because we should never get here.  Or we
> +		 * could just get rid of the memcmp() and this "if"
> +		 * clause completely.
> +		 */
> +		BUG("handle_using_dir_name_hash_icase(%s) did not exact match",
> +		    name);
> +	}
> +
> +	trace_printf_key(&trace_fsmonitor,
> +			 "fsmonitor_refresh_callback MAP: '%s' '%s'",
> +			 name, canonical_path.buf);
> +
> +	/*
> +	 * The dir-name-hash only tells us the corrected spelling of
> +	 * the prefix.  We have to use this canonical path to do a
> +	 * lookup in the cache-entry array so that we repeat the
> +	 * original search using the case-corrected spelling.
> +	 */
> +	strbuf_addch(&canonical_path, '/');
> +	pos = index_name_pos(istate, canonical_path.buf,
> +			     canonical_path.len);
> +	nr_in_cone = handle_path_with_trailing_slash(
> +		istate, canonical_path.buf, pos);
> +	strbuf_release(&canonical_path);
> +	return nr_in_cone;
> +}
> +
>  /*
>   * The daemon sent an observed pathname without a trailing slash.
>   * (This is the normal case.)  We do not know if it is a tracked or
> @@ -335,6 +443,19 @@ static void fsmonitor_refresh_callback(struct index_state *istate, char *name)
>  	else
>  		nr_in_cone = handle_path_without_trailing_slash(istate, name, pos);
>  
> +	/*
> +	 * If we did not find an exact match for this pathname or any
> +	 * cache-entries with this directory prefix and we're on a
> +	 * case-insensitive file system, try again using the name-hash
> +	 * and dir-name-hash.
> +	 */
> +	if (!nr_in_cone && ignore_case) {
> +		nr_in_cone = handle_using_name_hash_icase(istate, name);
> +		if (!nr_in_cone)
> +			nr_in_cone = handle_using_dir_name_hash_icase(
> +				istate, name);
> +	}
> +
>  	if (nr_in_cone)
>  		trace_printf_key(&trace_fsmonitor,
>  				 "fsmonitor_refresh_callback CNT: %d",
> diff --git a/t/t7527-builtin-fsmonitor.sh b/t/t7527-builtin-fsmonitor.sh
> index 830f2d9de33..730f3c7f810 100755
> --- a/t/t7527-builtin-fsmonitor.sh
> +++ b/t/t7527-builtin-fsmonitor.sh
> @@ -1051,7 +1051,7 @@ test_expect_success 'split-index and FSMonitor work well together' '
>  #
>  # The setup is a little contrived.
>  #
> -test_expect_failure CASE_INSENSITIVE_FS 'fsmonitor subdir case wrong on disk' '
> +test_expect_success CASE_INSENSITIVE_FS 'fsmonitor subdir case wrong on disk' '
>  	test_when_finished "stop_daemon_delete_repo subdir_case_wrong" &&
>  
>  	git init subdir_case_wrong &&
> @@ -1116,19 +1116,19 @@ test_expect_failure CASE_INSENSITIVE_FS 'fsmonitor subdir case wrong on disk' '
>  
>  	grep -q "dir1/DIR2/dir3/file3.*pos -3" "$PWD/subdir_case_wrong.log1" &&
>  
> +	# Verify that we get a mapping event to correct the case.
> +	grep -q "MAP:.*dir1/DIR2/dir3/file3.*dir1/dir2/dir3/file3" \
> +		"$PWD/subdir_case_wrong.log1" &&
> +
>  	# The refresh-callbacks should have caused "git status" to clear
>  	# the CE_FSMONITOR_VALID bit on each of those files and caused
>  	# the worktree scan to visit them and mark them as modified.
>  	grep -q " M AAA" "$PWD/subdir_case_wrong.out" &&
>  	grep -q " M zzz" "$PWD/subdir_case_wrong.out" &&
> -
> -	# Expect Breakage: with the case confusion, the "(pos -3)" causes
> -	# the client to not clear the CE_FSMONITOR_VALID bit and therefore
> -	# status will not rescan the file and therefore not report it as dirty.
>  	grep -q " M dir1/dir2/dir3/file3" "$PWD/subdir_case_wrong.out"
>  '
>  
> -test_expect_failure CASE_INSENSITIVE_FS 'fsmonitor file case wrong on disk' '
> +test_expect_success CASE_INSENSITIVE_FS 'fsmonitor file case wrong on disk' '
>  	test_when_finished "stop_daemon_delete_repo file_case_wrong" &&
>  
>  	git init file_case_wrong &&
> @@ -1242,14 +1242,20 @@ test_expect_failure CASE_INSENSITIVE_FS 'fsmonitor file case wrong on disk' '
>  	GIT_TRACE_FSMONITOR="$PWD/file_case_wrong-try3.log" \
>  		git -C file_case_wrong --no-optional-locks status --short \
>  			>"$PWD/file_case_wrong-try3.out" &&
> +
> +	# Verify that we get a mapping event to correct the case.
> +	grep -q "fsmonitor_refresh_callback MAP:.*dir1/dir2/dir3/FILE-3-A.*dir1/dir2/dir3/file-3-a" \
> +		"$PWD/file_case_wrong-try3.log" &&
> +	grep -q "fsmonitor_refresh_callback MAP:.*dir1/dir2/dir4/file-4-a.*dir1/dir2/dir4/FILE-4-A" \
> +		"$PWD/file_case_wrong-try3.log" &&
> +
>  	# FSEvents are in observed case.
>  	grep -q "fsmonitor_refresh_callback.*FILE-3-A.*pos -3" "$PWD/file_case_wrong-try3.log" &&
>  	grep -q "fsmonitor_refresh_callback.*file-4-a.*pos -9" "$PWD/file_case_wrong-try3.log" &&
>  
> -	# Expect Breakage: with the case confusion, the "(pos-3)" and
> -	# "(pos -9)" causes the client to not clear the CE_FSMONITOR_VALID
> -	# bit and therefore status will not rescan the files and therefore
> -	# not report them as dirty.
> +	# The refresh-callbacks should have caused "git status" to clear
> +	# the CE_FSMONITOR_VALID bit on each of those files and caused
> +	# the worktree scan to visit them and mark them as modified.
>  	grep -q " M dir1/dir2/dir3/file-3-a" "$PWD/file_case_wrong-try3.out" &&
>  	grep -q " M dir1/dir2/dir4/FILE-4-A" "$PWD/file_case_wrong-try3.out"
>  '
> -- 
> gitgitgadget