From 7b791d68562e4ce5ab57cbacb10a1ad4ee33956e Mon Sep 17 00:00:00 2001 From: Sunil Mushran Date: Tue, 16 Dec 2008 15:49:23 -0800 Subject: ocfs2/dlm: Fix race during lockres mastery dlm_get_lock_resource() is supposed to return a lock resource with a proper master. If multiple concurrent threads attempt to lookup the lockres for the same lockid while the lock mastery in underway, one or more threads are likely to return a lockres without a proper master. This patch makes the threads wait in dlm_get_lock_resource() while the mastery is underway, ensuring all threads return the lockres with a proper master. This issue is known to be limited to users using the flock() syscall. For all other fs operations, the ocfs2 dlmglue layer serializes the dlm op for each lockid. Users encountering this bug will see flock() return EINVAL and dmesg have the following error: ERROR: Dlm error "DLM_BADARGS" while calling dlmlock on resource : bad api args Reported-by: Coly Li Signed-off-by: Sunil Mushran Signed-off-by: Mark Fasheh --- fs/ocfs2/dlm/dlmmaster.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index cbf3abe24cdb..54e182a27caf 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -732,14 +732,21 @@ lookup: if (tmpres) { int dropping_ref = 0; + spin_unlock(&dlm->spinlock); + spin_lock(&tmpres->spinlock); + /* We wait for the other thread that is mastering the resource */ + if (tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN) { + __dlm_wait_on_lockres(tmpres); + BUG_ON(tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN); + } + if (tmpres->owner == dlm->node_num) { BUG_ON(tmpres->state & DLM_LOCK_RES_DROPPING_REF); dlm_lockres_grab_inflight_ref(dlm, tmpres); } else if (tmpres->state & DLM_LOCK_RES_DROPPING_REF) dropping_ref = 1; spin_unlock(&tmpres->spinlock); - spin_unlock(&dlm->spinlock); /* wait until done messaging the master, drop our ref to allow * the lockres to be purged, start over. */ -- cgit v1.2.3