From: piaojun Date: Thu, 5 Apr 2018 23:19:11 +0000 (-0700) Subject: ocfs2/dlm: wait for dlm recovery done when migrating all lock resources X-Git-Tag: v4.19~1277^2~101 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=60c7ec9ee4a3410c2cb08850102d363c7e207f48;p=platform%2Fkernel%2Flinux-rpi3.git ocfs2/dlm: wait for dlm recovery done when migrating all lock resources Wait for dlm recovery done when migrating all lock resources in case that new lock resource left after leaving dlm domain. And the left lock resource will cause other nodes BUG. NodeA NodeB NodeC umount: dlm_unregister_domain() dlm_migrate_all_locks() NodeB down do recovery for NodeB and collect a new lockres form other live nodes: dlm_do_recovery dlm_remaster_locks dlm_request_all_locks: dlm_mig_lockres_handler dlm_new_lockres __dlm_insert_lockres at last NodeA become the master of the new lockres and leave domain: dlm_leave_domain() mount: dlm_join_domain() touch file and request for the owner of the new lockres, but all the other nodes said 'NO', so NodeC decide to be the owner, and send do assert msg to other nodes: dlmlock() dlm_get_lock_resource() dlm_do_assert_master() other nodes receive the msg and found two masters exist. at last cause BUG in dlm_assert_master_handler() -->BUG(); Link: http://lkml.kernel.org/r/5AAA6E25.7090303@huawei.com Fixes: bc9838c4d44a ("dlm: allow dlm do recovery during shutdown") Signed-off-by: Jun Piao Reviewed-by: Alex Chen Reviewed-by: Yiwen Jiang Acked-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index 953c200..d06e27e 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -140,6 +140,7 @@ struct dlm_ctxt u8 node_num; u32 key; u8 joining_node; + u8 migrate_done; /* set to 1 means node has migrated all lock resources */ wait_queue_head_t dlm_join_events; unsigned long live_nodes_map[BITS_TO_LONGS(O2NM_MAX_NODES)]; unsigned long domain_map[BITS_TO_LONGS(O2NM_MAX_NODES)]; diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 25b76f0..425081b 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -461,6 +461,19 @@ redo_bucket: cond_resched_lock(&dlm->spinlock); num += n; } + + if (!num) { + if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) { + mlog(0, "%s: perhaps there are more lock resources " + "need to be migrated after dlm recovery\n", dlm->name); + ret = -EAGAIN; + } else { + mlog(0, "%s: we won't do dlm recovery after migrating " + "all lock resources\n", dlm->name); + dlm->migrate_done = 1; + } + } + spin_unlock(&dlm->spinlock); wake_up(&dlm->dlm_thread_wq); @@ -2038,6 +2051,8 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain, dlm->joining_node = DLM_LOCK_RES_OWNER_UNKNOWN; init_waitqueue_head(&dlm->dlm_join_events); + dlm->migrate_done = 0; + dlm->reco.new_master = O2NM_INVALID_NODE_NUM; dlm->reco.dead_node = O2NM_INVALID_NODE_NUM; diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 86204b8..b454eb3 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -423,12 +423,11 @@ void dlm_wait_for_recovery(struct dlm_ctxt *dlm) static void dlm_begin_recovery(struct dlm_ctxt *dlm) { - spin_lock(&dlm->spinlock); + assert_spin_locked(&dlm->spinlock); BUG_ON(dlm->reco.state & DLM_RECO_STATE_ACTIVE); printk(KERN_NOTICE "o2dlm: Begin recovery on domain %s for node %u\n", dlm->name, dlm->reco.dead_node); dlm->reco.state |= DLM_RECO_STATE_ACTIVE; - spin_unlock(&dlm->spinlock); } static void dlm_end_recovery(struct dlm_ctxt *dlm) @@ -456,6 +455,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) spin_lock(&dlm->spinlock); + if (dlm->migrate_done) { + mlog(0, "%s: no need do recovery after migrating all " + "lock resources\n", dlm->name); + spin_unlock(&dlm->spinlock); + return 0; + } + /* check to see if the new master has died */ if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM && test_bit(dlm->reco.new_master, dlm->recovery_map)) { @@ -490,12 +496,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) mlog(0, "%s(%d):recovery thread found node %u in the recovery map!\n", dlm->name, task_pid_nr(dlm->dlm_reco_thread_task), dlm->reco.dead_node); - spin_unlock(&dlm->spinlock); /* take write barrier */ /* (stops the list reshuffling thread, proxy ast handling) */ dlm_begin_recovery(dlm); + spin_unlock(&dlm->spinlock); + if (dlm->reco.new_master == dlm->node_num) goto master_here;