Fix for bug #45143 "All connections hang on concurrent ALTER TABLE".

Concurrent execution of statements which require non-table-level
write locks on several instances of the same table (such as
SELECT ... FOR UPDATE which uses same InnoDB table twice or a DML
statement which invokes trigger which tries to update same InnoDB
table directly and through stored function) and statements which
required table-level locks on this table (e.g. LOCK TABLE ... WRITE,
ALTER TABLE, ...) might have resulted in a deadlock.

The problem occured when a thread tried to acquire write lock
(TL_WRITE_ALLOW_WRITE) on the table but had to wait since there was
a pending write lock (TL_WRITE, TL_WRITE_ALLOW_READ) on this table
and we failed to detect that this thread already had another instance
of write lock on it (so in fact we were trying to acquire recursive
lock) because there was also another thread holding write lock on the
table (also TL_WRITE_ALLOW_WRITE). When the latter thread released
its lock neither the first thread nor the thread trying to acquire
TL_WRITE/TL_WRITE_ALLOW_READ were woken up (as table was still write
locked by the first thread) so we ended up with a deadlock.

This patch solves this problem by ensuring that thread which
already has write lock on the table won't wait when it tries
to acquire second write lock on the same table.

mysql-test/r/lock_sync.result:
  Added test case for bug #45143 "All connections hang on concurrent
  ALTER TABLE".
mysql-test/t/lock_sync.test:
  Added test case for bug #45143 "All connections hang on concurrent
  ALTER TABLE".
mysys/thr_lock.c:
  Ensured that thread can acquire write lock on the table without
  waiting if it already has write lock on it even if there are other
  threads holding write locks on this table (this is normal situation
  for, e.g., TL_WRITE_ALLOW_WRITE type of lock).
  
  Adjusted comments to better explain why it is OK to do so and added
  asserts to prevent introduction of scenarios in which this can cause
  problems.

1 files changed, 115 insertions, 0 deletions

diff --git a/mysql-test/t/lock_sync.test b/mysql-test/t/lock_sync.test
new file mode 100644
index 00000000000..dcfc5a48ee7
--- /dev/null
+++ b/mysql-test/t/lock_sync.test
@@ -0,0 +1,115 @@
+#
+# Locking related tests which use DEBUG_SYNC facility.
+#
+--source include/have_debug_sync.inc
+# We need InnoDB to be able use TL_WRITE_ALLOW_WRITE type of locks in our tests.
+--source include/have_innodb.inc
+
+# Save the initial number of concurrent sessions.
+--source include/count_sessions.inc
+
+
+--echo #
+--echo # Test for bug #45143 "All connections hang on concurrent ALTER TABLE".
+--echo #
+--echo # Concurrent execution of statements which required weak write lock
+--echo # (TL_WRITE_ALLOW_WRITE) on several instances of the same table and
+--echo # statements which tried to acquire stronger write lock (TL_WRITE,
+--echo # TL_WRITE_ALLOW_READ) on this table might have led to deadlock.
+--disable_warnings
+drop table if exists t1;
+--enable_warnings
+--echo # Create auxiliary connections used through the test.
+connect (con_bug45143_1,localhost,root,,test,,);
+connect (con_bug45143_3,localhost,root,,test,,);
+connect (con_bug45143_2,localhost,root,,test,,);
+connection default;
+--echo # Reset DEBUG_SYNC facility before using it.
+set debug_sync= 'RESET';
+--echo # Turn off logging so calls to locking subsystem performed
+--echo # for general_log table won't interfere with our test.
+set @old_general_log = @@global.general_log;
+set @@global.general_log= OFF;
+
+create table t1 (i int) engine=InnoDB;
+insert into t1 values (1);
+--echo # Prepare user lock which will be used for resuming execution of
+--echo # the first statement after it acquires TL_WRITE_ALLOW_WRITE lock.
+select get_lock("lock_bug45143_wait", 0);
+
+--echo # Switch to connection 'con_bug45143_1'.
+connection con_bug45143_1;
+--echo # Sending:
+--send insert into t1 values (get_lock("lock_bug45143_wait", 100));
+
+--echo # Switch to connection 'con_bug45143_2'.
+connection con_bug45143_2;
+--echo # Wait until the above INSERT takes TL_WRITE_ALLOW_WRITE lock on 't1'
+--echo # and then gets blocked on user lock 'lock_bug45143_wait'.
+let $wait_condition= select count(*)= 1 from information_schema.processlist
+                       where state= 'User lock' and
+                             info='insert into t1 values (get_lock("lock_bug45143_wait", 100))';
+--source include/wait_condition.inc
+--echo # Ensure that upcoming SELECT waits after acquiring TL_WRITE_ALLOW_WRITE
+--echo # lock for the first instance of 't1'.
+set debug_sync='thr_multi_lock_after_thr_lock SIGNAL parked WAIT_FOR go';
+--echo # Sending:
+--send select count(*) > 0 from t1 as a, t1 as b for update;
+
+--echo # Switch to connection 'con_bug45143_3'.
+connection con_bug45143_3;
+--echo # Wait until the above SELECT ... FOR UPDATE is blocked after
+--echo # acquiring lock for the the first instance of 't1'.
+set debug_sync= 'now WAIT_FOR parked';
+--echo # Send LOCK TABLE statement which will try to get TL_WRITE lock on 't1':
+--send lock table t1 write;
+
+--echo # Switch to connection 'default'.
+connection default;
+--echo # Wait until this LOCK TABLES statement starts waiting for table lock.
+let $wait_condition= select count(*)= 1 from information_schema.processlist
+                       where state= 'Locked' and
+                             info='lock table t1 write';
+--source include/wait_condition.inc
+--echo # Allow SELECT ... FOR UPDATE to resume.
+--echo # Since it already has TL_WRITE_ALLOW_WRITE lock on the first instance
+--echo # of 't1' it should be able to get lock on the second instance without
+--echo # waiting, even although there is another thread which has such lock
+--echo # on this table and also there is a thread waiting for a TL_WRITE on it.
+set debug_sync= 'now SIGNAL go';
+
+--echo # Switch to connection 'con_bug45143_2'.
+connection con_bug45143_2;
+--echo # Reap SELECT ... FOR UPDATE
+--reap
+
+--echo # Switch to connection 'default'.
+connection default;
+--echo # Resume execution of the INSERT statement.
+select release_lock("lock_bug45143_wait");
+
+--echo # Switch to connection 'con_bug45143_1'.
+connection con_bug45143_1;
+--echo # Reap INSERT statement.
+--reap
+
+--echo # Switch to connection 'con_bug45143_3'.
+connection con_bug45143_3;
+--echo # Reap LOCK TABLES statement.
+--reap
+unlock tables;
+
+--echo # Switch to connection 'default'.
+connection default;
+--echo # Do clean-up.
+disconnect con_bug45143_1;
+disconnect con_bug45143_2;
+disconnect con_bug45143_3;
+set debug_sync= 'RESET';
+set @@global.general_log= @old_general_log;
+drop table t1;
+
+
+# Check that all connections opened by test cases in this file are really
+# gone so execution of other tests won't be affected by their presence.
+--source include/wait_until_count_sessions.inc