From 7dc102b737e9f49dac426161294cb2d326a97d8e Mon Sep 17 00:00:00 2001 From: Sunil Mushran Date: Tue, 3 Feb 2009 12:37:13 -0800 Subject: ocfs2/dlm: Retract fix for race between purge and migrate Mainline commit d4f7e650e55af6b235871126f747da88600e8040 attempts to delay the dlm_thread from sending the drop ref message if the lockres is being migrated. The problem is that we make the dlm_thread wait for the migration to complete. This causes a deadlock as dlm_thread also participates in the lockres migration process. A better fix for the original oss bugzilla#1012 is in testing. Signed-off-by: Sunil Mushran Acked-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/dlm/dlmthread.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'fs/ocfs2/dlm') diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c index d1295203029..4060bb328bc 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -181,8 +181,7 @@ static int dlm_purge_lockres(struct dlm_ctxt *dlm, spin_lock(&res->spinlock); /* This ensures that clear refmap is sent after the set */ - __dlm_wait_on_lockres_flags(res, (DLM_LOCK_RES_SETREF_INPROG | - DLM_LOCK_RES_MIGRATING)); + __dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG); spin_unlock(&res->spinlock); /* clear our bit from the master's refmap, ignore errors */ -- cgit v1.2.3 From dabc47de7a23f57522dc762d9d2ad875700d3497 Mon Sep 17 00:00:00 2001 From: Sunil Mushran Date: Tue, 3 Feb 2009 12:37:15 -0800 Subject: ocfs2/dlm: Use ast_lock to protect ast_list The code was using dlm->spinlock instead of dlm->ast_lock to protect the ast_list. This patch fixes the issue. Signed-off-by: Sunil Mushran Acked-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/dlm/dlmunlock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/ocfs2/dlm') diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index 86ca085ef32..fcf879ed693 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -117,11 +117,11 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, else BUG_ON(res->owner == dlm->node_num); - spin_lock(&dlm->spinlock); + spin_lock(&dlm->ast_lock); /* We want to be sure that we're not freeing a lock * that still has AST's pending... */ in_use = !list_empty(&lock->ast_list); - spin_unlock(&dlm->spinlock); + spin_unlock(&dlm->ast_lock); if (in_use) { mlog(ML_ERROR, "lockres %.*s: Someone is calling dlmunlock " "while waiting for an ast!", res->lockname.len, -- cgit v1.2.3 From 53ecd25e148615e0ed2a72635cc76f4773f97f90 Mon Sep 17 00:00:00 2001 From: Sunil Mushran Date: Tue, 3 Feb 2009 12:37:16 -0800 Subject: ocfs2/dlm: Make dlm_assert_master_handler() kill itself instead of the asserter In dlm_assert_master_handler(), if we get an incorrect assert master from a node that, we reply with EINVAL asking the asserter to die. The problem is that an assert is sent after so many hoops, it is invariably the node that thinks the asserter is wrong, is actually wrong. So instead of killing the asserter, this patch kills the assertee. This patch papers over a race that is still being addressed. Signed-off-by: Sunil Mushran Acked-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/dlm/dlmmaster.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'fs/ocfs2/dlm') diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 54e182a27ca..0a281394785 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1849,12 +1849,12 @@ int dlm_assert_master_handler(struct o2net_msg *msg, u32 len, void *data, if (!mle) { if (res->owner != DLM_LOCK_RES_OWNER_UNKNOWN && res->owner != assert->node_idx) { - mlog(ML_ERROR, "assert_master from " - "%u, but current owner is " - "%u! (%.*s)\n", - assert->node_idx, res->owner, - namelen, name); - goto kill; + mlog(ML_ERROR, "DIE! Mastery assert from %u, " + "but current owner is %u! (%.*s)\n", + assert->node_idx, res->owner, namelen, + name); + __dlm_print_one_lock_resource(res); + BUG(); } } else if (mle->type != DLM_MLE_MIGRATION) { if (res->owner != DLM_LOCK_RES_OWNER_UNKNOWN) { -- cgit v1.2.3