hashmap: add API to disable item counting when threadedjh/hashmap-disable-counting

This is to address concerns raised by ThreadSanitizer on the mailing list
about threaded unprotected R/W access to map.size with my previous "disallow
rehash" change (0607e10009ee4e37cb49b4cec8d28a9dda1656a4).

See:
https://public-inbox.org/git/adb37b70139fd1e2bac18bfd22c8b96683ae18eb.1502780344.git.martin.agren@gmail.com/

Add API to hashmap to disable item counting and thus automatic rehashing.
Also include API to later re-enable them.

When item counting is disabled, the map.size field is invalid.  So to
prevent accidents, the field has been renamed and an accessor function
hashmap_get_size() has been added.  All direct references to this
field have been been updated.  And the name of the field changed
to map.private_size to communicate this.

Here is the relevant output from ThreadSanitizer showing the problem:

WARNING: ThreadSanitizer: data race (pid=10554)
  Read of size 4 at 0x00000082d488 by thread T2 (mutexes: write M16):
    #0 hashmap_add hashmap.c:209
    #1 hash_dir_entry_with_parent_and_prefix name-hash.c:302
    #2 handle_range_dir name-hash.c:347
    #3 handle_range_1 name-hash.c:415
    #4 lazy_dir_thread_proc name-hash.c:471
    #5 <null> <null>

  Previous write of size 4 at 0x00000082d488 by thread T1 (mutexes: write M31):
    #0 hashmap_add hashmap.c:209
    #1 hash_dir_entry_with_parent_and_prefix name-hash.c:302
    #2 handle_range_dir name-hash.c:347
    #3 handle_range_1 name-hash.c:415
    #4 handle_range_dir name-hash.c:380
    #5 handle_range_1 name-hash.c:415
    #6 lazy_dir_thread_proc name-hash.c:471
    #7 <null> <null>

Martin gives instructions for running TSan on test t3008 in this post:
https://public-inbox.org/git/CAN0heSoJDL9pWELD6ciLTmWf-a=oyxe4EXXOmCKvsG5MSuzxsA@mail.gmail.com/

Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 17 insertions, 9 deletions

diff --git a/hashmap.c b/hashmap.c
index 9b6a12859b..d42f01ff5a 100644
--- a/hashmap.c
+++ b/hashmap.c
@@ -116,9 +116,6 @@ static void rehash(struct hashmap *map, unsigned int newsize)
 	unsigned int i, oldsize = map->tablesize;
 	struct hashmap_entry **oldtable = map->table;
 
-	if (map->disallow_rehash)
-		return;
-
 	alloc_table(map, newsize);
 	for (i = 0; i < oldsize; i++) {
 		struct hashmap_entry *e = oldtable[i];
@@ -166,6 +163,12 @@ void hashmap_init(struct hashmap *map, hashmap_cmp_fn equals_function,
 	while (initial_size > size)
 		size <<= HASHMAP_RESIZE_BITS;
 	alloc_table(map, size);
+
+	/*
+	 * Keep track of the number of items in the map and
+	 * allow the map to automatically grow as necessary.
+	 */
+	map->do_count_items = 1;
 }
 
 void hashmap_free(struct hashmap *map, int free_entries)
@@ -206,9 +209,11 @@ void hashmap_add(struct hashmap *map, void *entry)
 	map->table[b] = entry;
 
 	/* fix size and rehash if appropriate */
-	map->size++;
-	if (map->size > map->grow_at)
-		rehash(map, map->tablesize << HASHMAP_RESIZE_BITS);
+	if (map->do_count_items) {
+		map->private_size++;
+		if (map->private_size > map->grow_at)
+			rehash(map, map->tablesize << HASHMAP_RESIZE_BITS);
+	}
 }
 
 void *hashmap_remove(struct hashmap *map, const void *key, const void *keydata)
@@ -224,9 +229,12 @@ void *hashmap_remove(struct hashmap *map, const void *key, const void *keydata)
 	old->next = NULL;
 
 	/* fix size and rehash if appropriate */
-	map->size--;
-	if (map->size < map->shrink_at)
-		rehash(map, map->tablesize >> HASHMAP_RESIZE_BITS);
+	if (map->do_count_items) {
+		map->private_size--;
+		if (map->private_size < map->shrink_at)
+			rehash(map, map->tablesize >> HASHMAP_RESIZE_BITS);
+	}
+
 	return old;
 }