fsmonitor: don't fill bitmap with entries to be removed

fill_fsmonitor_bitmap was populating fsmonitor_dirty
with all entries in the cache, even those that have
been marked for removal.  This caused a problem when
subsequent git commands read the index, as the bit's
position in fsmonitor_dirty would no longer match the
index in the cache.  Additionally, the number of entries
in fsmonitor_dirty could exceed the number of entries in
the cache.  If the number of entries in fsmonitor_dirty
exceeded the number of entries in the cache it resulted
in a segfault when tweak_fsmonitor was called because
ewah_each_bit would go beyond the bounds of the cache.

Signed-off-by: William Baker <[email protected]>

Author: wilbaker

fsmonitor.c

@@ -14,8 +14,13 @@ struct trace_key trace_fsmonitor = TRACE_KEY_INIT(FSMONITOR);
 static void fsmonitor_ewah_callback(size_t pos, void *is)
 {
 	struct index_state *istate = (struct index_state *)is;
-	struct cache_entry *ce = istate->cache[pos];
+	struct cache_entry *ce;
+	
+	if (pos >= istate->cache_nr)
+		BUG("fsmonitor_dirty has more entries than the index (%"PRIuMAX" >= %"PRIuMAX")",
+		    (uintmax_t)pos, (uintmax_t)istate->cache_nr);
 
+	ce = istate->cache[pos];
 	ce->ce_flags &= ~CE_FSMONITOR_VALID;
 }
 
@@ -50,17 +55,24 @@ int read_fsmonitor_extension(struct index_state *istate, const void *data,
 	}
 	istate->fsmonitor_dirty = fsmonitor_dirty;
 
+	if (istate->fsmonitor_dirty->bit_size > istate->cache_nr)
+		BUG("fsmonitor_dirty has more entries than the index (%"PRIuMAX" > %"PRIuMAX")",
+		    (uintmax_t)istate->fsmonitor_dirty->bit_size, (uintmax_t)istate->cache_nr);
+
 	trace_printf_key(&trace_fsmonitor, "read fsmonitor extension successful");
 	return 0;
 }
 
 void fill_fsmonitor_bitmap(struct index_state *istate)
 {
-	unsigned int i;
+	unsigned int i, skipped = 0;
 	istate->fsmonitor_dirty = ewah_new();
-	for (i = 0; i < istate->cache_nr; i++)
-		if (!(istate->cache[i]->ce_flags & CE_FSMONITOR_VALID))
-			ewah_set(istate->fsmonitor_dirty, i);
+	for (i = 0; i < istate->cache_nr; i++) {
+		if (istate->cache[i]->ce_flags & CE_REMOVE)
+			skipped++;
+		else if (!(istate->cache[i]->ce_flags & CE_FSMONITOR_VALID))
+			ewah_set(istate->fsmonitor_dirty, i - skipped);
+	}
 }
 
 void write_fsmonitor_extension(struct strbuf *sb, struct index_state *istate)
@@ -71,6 +83,10 @@ void write_fsmonitor_extension(struct strbuf *sb, struct index_state *istate)
 	uint32_t ewah_size = 0;
 	int fixup = 0;
 
+	if (istate->fsmonitor_dirty->bit_size > istate->cache_nr)
+		BUG("fsmonitor_dirty has more entries than the index (%"PRIuMAX" > %"PRIuMAX")",
+		    (uintmax_t)istate->fsmonitor_dirty->bit_size, (uintmax_t)istate->cache_nr);
+
 	put_be32(&hdr_version, INDEX_EXTENSION_VERSION);
 	strbuf_add(sb, &hdr_version, sizeof(uint32_t));
 
@@ -236,6 +252,9 @@ void tweak_fsmonitor(struct index_state *istate)
 			}
 
 			/* Mark all previously saved entries as dirty */
+			if (istate->fsmonitor_dirty->bit_size > istate->cache_nr)
+				BUG("fsmonitor_dirty has more entries than the index (%"PRIuMAX" > %"PRIuMAX")",
+				    (uintmax_t)istate->fsmonitor_dirty->bit_size, (uintmax_t)istate->cache_nr);
 			ewah_each_bit(istate->fsmonitor_dirty, fsmonitor_ewah_callback, istate);
 
 			/* Now mark the untracked cache for fsmonitor usage */

t/t7519-status-fsmonitor.sh

@@ -354,4 +354,16 @@ test_expect_success 'discard_index() also discards fsmonitor info' '
 	test_cmp expect actual
 '
 
+# Use test files that start with 'z' so that the entries being added
+# and removed appear at the end of the index.
+test_expect_success 'status succeeds after staging/unstaging ' '
+	test_commit initial &&
+	removed=$(test_seq 1 100 | sed "s/^/z/") &&
+	touch $removed &&
+	git add $removed &&
+	test_config core.fsmonitor "$TEST_DIRECTORY/t7519/fsmonitor-env" &&
+	FSMONITOR_LIST="$removed" git restore -S $removed &&
+	FSMONITOR_LIST="$removed" git status
+'
+
 test_done

t/t7519/fsmonitor-env

@@ -0,0 +1,24 @@
+#!/bin/sh
+#
+# An test hook script to integrate with git to test fsmonitor.
+#
+# The hook is passed a version (currently 1) and a time in nanoseconds
+# formatted as a string and outputs to stdout all files that have been
+# modified since the given time. Paths must be relative to the root of
+# the working tree and separated by a single NUL.
+#
+#echo "$0 $*" >&2
+
+if test "$#" -ne 2
+then
+	echo "$0: exactly 2 arguments expected" >&2
+	exit 2
+fi
+
+if test "$1" != 1
+then
+	echo "Unsupported core.fsmonitor hook version." >&2
+	exit 1
+fi
+
+printf '%s\n' $FSMONITOR_LIST