From c70115b4b1a8c197b9b829b1fd15d578a3ffcdc3 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Tue, 29 Jul 2008 01:13:44 -0700 Subject: [PATCH] Teach gitlinks to ie_modified() and ce_modified_check_fs() The ie_modified() function is the workhorse for refresh_cache_entry(), i.e. checking if an index entry that is stat-dirty actually has changes. After running quicker check to compare cached stat information with results from the latest lstat(2) to answer "has modification" early, the code goes on to check if there really is a change by comparing the staged data with what is on the filesystem by asking ce_modified_check_fs(). However, this function always said "no change" for any gitlinks that has a directory at the corresponding path. This made ie_modified() to miss actual changes in the subproject. The patch fixes this first by modifying an existing short-circuit logic before calling the ce_modified_check_fs() function. It knows that for any filesystem entity to which ie_match_stat() says its data has changed, if its cached size is nonzero then the contents cannot match, which is a correct optimization only for blob objects. We teach gitlink objects to this special case, as we already know that any gitlink that ie_match_stat() says is modified is indeed modified at this point in the codepath. With the above change, we could leave ce_modified_check_fs() broken, but it also futureproofs the code by teaching it to use ce_compare_gitlink(), instead of assuming (incorrectly) that any directory is unchanged. Originally noticed by Alex Riesen on Cygwin. Signed-off-by: Junio C Hamano --- read-cache.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/read-cache.c b/read-cache.c index 1cae361c6..2c03ec306 100644 --- a/read-cache.c +++ b/read-cache.c @@ -147,7 +147,7 @@ static int ce_modified_check_fs(struct cache_entry *ce, struct stat *st) break; case S_IFDIR: if (S_ISGITLINK(ce->ce_mode)) - return 0; + return ce_compare_gitlink(ce) ? DATA_CHANGED : 0; default: return TYPE_CHANGED; } @@ -187,6 +187,7 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st) changed |= TYPE_CHANGED; break; case S_IFGITLINK: + /* We ignore most of the st_xxx fields for gitlinks */ if (!S_ISDIR(st->st_mode)) changed |= TYPE_CHANGED; else if (ce_compare_gitlink(ce)) @@ -293,11 +294,22 @@ int ie_modified(const struct index_state *istate, if (changed & (MODE_CHANGED | TYPE_CHANGED)) return changed; - /* Immediately after read-tree or update-index --cacheinfo, - * the length field is zero. For other cases the ce_size - * should match the SHA1 recorded in the index entry. + /* + * Immediately after read-tree or update-index --cacheinfo, + * the length field is zero, as we have never even read the + * lstat(2) information once, and we cannot trust DATA_CHANGED + * returned by ie_match_stat() which in turn was returned by + * ce_match_stat_basic() to signal that the filesize of the + * blob changed. We have to actually go to the filesystem to + * see if the contents match, and if so, should answer "unchanged". + * + * The logic does not apply to gitlinks, as ce_match_stat_basic() + * already has checked the actual HEAD from the filesystem in the + * subproject. If ie_match_stat() already said it is different, + * then we know it is. */ - if ((changed & DATA_CHANGED) && ce->ce_size != 0) + if ((changed & DATA_CHANGED) && + (S_ISGITLINK(ce->ce_mode) || ce->ce_size != 0)) return changed; changed_fs = ce_modified_check_fs(ce, st); @@ -1326,6 +1338,11 @@ static void ce_smudge_racily_clean_entry(struct cache_entry *ce) * falsely clean entry due to touch-update-touch race, so we leave * everything else as they are. We are called for entries whose * ce_mtime match the index file mtime. + * + * Note that this actually does not do much for gitlinks, for + * which ce_match_stat_basic() always goes to the actual + * contents. The caller checks with is_racy_timestamp() which + * always says "no" for gitlinks, so we are not called for them ;-) */ struct stat st; -- 2.30.2