From 564b3472099ab9e61d8c108d5c8d1b3d6f5de423 Mon Sep 17 00:00:00 2001 From: Thomas Munro Date: Mon, 19 Jun 2023 16:28:02 +1200 Subject: [PATCH v3 1/3] Fix race in SSI interaction with empty btrees. When predicate-locking btrees, we have a special case for completely empty btrees, since there is no page to lock. This was racy, because, without buffer lock held, a matching key could be inserted between the _bt_search() and the PredicateLockRelation() calls. Fix, by rechecking _bt_search() after taking the relation-level SIREAD lock, if using SERIALIZABLE isolation and an empty btree is discovered. Back-patch to all supported releases. Reported-by: Artem Anisimov Reviewed-by: Dmitry Dolgov <9erthalion6@gmail.com> Discussion: https://postgr.es/m/17949-a0f17035294a55e2%40postgresql.org --- src/backend/access/nbtree/nbtsearch.c | 39 +++++++++++++++++---------- 1 file changed, 25 insertions(+), 14 deletions(-) diff --git a/src/backend/access/nbtree/nbtsearch.c b/src/backend/access/nbtree/nbtsearch.c index 7e05e58676..2477b7aefb 100644 --- a/src/backend/access/nbtree/nbtsearch.c +++ b/src/backend/access/nbtree/nbtsearch.c @@ -1381,23 +1381,34 @@ _bt_first(IndexScanDesc scan, ScanDirection dir) if (!BufferIsValid(buf)) { /* - * We only get here if the index is completely empty. Lock relation - * because nothing finer to lock exists. + * Since we have no pages locked, it's possible for another + * transaction to insert data between _bt_search() and + * PredicateLockRelation(). We have to try again after taking a + * relation-level predicate lock, to close a narrow window where we + * wouldn't scan concurrently inserted tuples, but the writer wouldn't + * see our predicate lock. */ - PredicateLockRelation(rel, scan->xs_snapshot); - - /* - * mark parallel scan as done, so that all the workers can finish - * their scan - */ - _bt_parallel_done(scan); - BTScanPosInvalidate(so->currPos); + if (IsolationIsSerializable()) + { + PredicateLockRelation(rel, scan->xs_snapshot); + stack = _bt_search(rel, NULL, &inskey, &buf, BT_READ, + scan->xs_snapshot); + _bt_freestack(stack); + } - return false; + if (!BufferIsValid(buf)) + { + /* + * Mark parallel scan as done, so that all the workers can finish + * their scan. + */ + _bt_parallel_done(scan); + BTScanPosInvalidate(so->currPos); + return false; + } } - else - PredicateLockPage(rel, BufferGetBlockNumber(buf), - scan->xs_snapshot); + + PredicateLockPage(rel, BufferGetBlockNumber(buf), scan->xs_snapshot); _bt_initialize_more_data(so, dir); -- 2.40.1