racy-git: an empty blob has a fixed object name

We use size=0 as the magic token to say the entry is known to be racily
clean, but a sequence that does:

 - update the path with a non-empty blob and write the index;
 - update an unrelated path and write the index -- this smudges
   the above entry;
 - truncate the path to size zero.

would make both the size field for the path in the index and the size on
the filesystem zero.  We should not mistake it as a clean index entry.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/read-cache.c b/read-cache.c
index a92b25b59bf0e096942bca126542a1ea411b525b..6fa3c21148979791f18bc0b5c3ed76952acad9ff 100644 (file)
--- a/read-cache.c
+++ b/read-cache.c
@@ -197,6 +197,16 @@ static int ce_modified_check_fs(struct cache_entry *ce, struct stat *st)
        return 0;
 }
 
+static int is_empty_blob_sha1(const unsigned char *sha1)
+{
+       static const unsigned char empty_blob_sha1[20] = {
+               0xe6,0x9d,0xe2,0x9b,0xb2,0xd1,0xd6,0x43,0x4b,0x8b,
+               0x29,0xae,0x77,0x5a,0xd8,0xc2,0xe4,0x8c,0x53,0x91
+       };
+
+       return !hashcmp(sha1, empty_blob_sha1);
+}
+
 static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
 {
        unsigned int changed = 0;
@@ -252,6 +262,12 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
        if (ce->ce_size != (unsigned int) st->st_size)
                changed |= DATA_CHANGED;
 
+       /* Racily smudged entry? */
+       if (!ce->ce_size) {
+               if (!is_empty_blob_sha1(ce->sha1))
+                       changed |= DATA_CHANGED;
+       }
+
        return changed;
 }