The patch titled Subject: ocfs2-dlm-fix-race-between-convert-and-recovery-v3 has been removed from the -mm tree. Its filename was ocfs2-dlm-fix-race-between-convert-and-recovery-v3.patch This patch was dropped because it was folded into ocfs2-dlm-fix-race-between-convert-and-recovery.patch ------------------------------------------------------ From: Joseph Qi <joseph.qi@xxxxxxxxxx> Subject: ocfs2-dlm-fix-race-between-convert-and-recovery-v3 Signed-off-by: Joseph Qi <joseph.qi@xxxxxxxxxx> Reported-by: Yiwen Jiang <jiangyiwen@xxxxxxxxxx> Cc: Junxiao Bi <junxiao.bi@xxxxxxxxxx> Cc: Mark Fasheh <mfasheh@xxxxxxx> Cc: Joel Becker <jlbec@xxxxxxxxxxxx> Cc: Tariq Saeed <tariq.x.saeed@xxxxxxxxxx> Cc: Junxiao Bi <junxiao.bi@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- fs/ocfs2/dlm/dlmcommon.h | 1 + fs/ocfs2/dlm/dlmconvert.c | 13 ++++++++++++- fs/ocfs2/dlm/dlmdebug.c | 7 ++++--- fs/ocfs2/dlm/dlmlock.c | 1 + fs/ocfs2/dlm/dlmrecovery.c | 10 +++++++++- 5 files changed, 27 insertions(+), 5 deletions(-) diff -puN fs/ocfs2/dlm/dlmcommon.h~ocfs2-dlm-fix-race-between-convert-and-recovery-v3 fs/ocfs2/dlm/dlmcommon.h --- a/fs/ocfs2/dlm/dlmcommon.h~ocfs2-dlm-fix-race-between-convert-and-recovery-v3 +++ a/fs/ocfs2/dlm/dlmcommon.h @@ -370,6 +370,7 @@ struct dlm_lock struct dlm_lockstatus *lksb; unsigned ast_pending:1, bast_pending:1, + convert_pending:1, lock_pending:1, cancel_pending:1, unlock_pending:1, diff -puN fs/ocfs2/dlm/dlmconvert.c~ocfs2-dlm-fix-race-between-convert-and-recovery-v3 fs/ocfs2/dlm/dlmconvert.c --- a/fs/ocfs2/dlm/dlmconvert.c~ocfs2-dlm-fix-race-between-convert-and-recovery-v3 +++ a/fs/ocfs2/dlm/dlmconvert.c @@ -262,6 +262,7 @@ enum dlm_status dlmconvert_remote(struct struct dlm_lock *lock, int flags, int type) { enum dlm_status status; + u8 old_owner = res->owner; mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type, lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS); @@ -291,6 +292,7 @@ enum dlm_status dlmconvert_remote(struct /* move lock to local convert queue */ /* do not alter lock refcount. switching lists. */ list_move_tail(&lock->list, &res->converting); + lock->convert_pending = 1; lock->ml.convert_type = type; if (flags & LKM_VALBLK) { @@ -314,11 +316,20 @@ enum dlm_status dlmconvert_remote(struct spin_lock(&res->spinlock); res->state &= ~DLM_LOCK_RES_IN_PROGRESS; - /* if it failed, move it back to granted queue */ + lock->convert_pending = 0; + /* if it failed, move it back to granted queue. + * if master returns DLM_NORMAL and then down before sending ast, + * it may have already been moved to granted queue, reset to + * DLM_RECOVERING and retry convert */ if (status != DLM_NORMAL) { if (status != DLM_NOTQUEUED) dlm_error(status); dlm_revert_pending_convert(res, lock); + } else if ((res->state & DLM_LOCK_RES_RECOVERING) || + (old_owner != res->owner)) { + mlog(0, "res %.*s is in recovering or has been recovered.\n", + res->lockname.len, res->lockname.name); + status = DLM_RECOVERING; } bail: spin_unlock(&res->spinlock); diff -puN fs/ocfs2/dlm/dlmdebug.c~ocfs2-dlm-fix-race-between-convert-and-recovery-v3 fs/ocfs2/dlm/dlmdebug.c --- a/fs/ocfs2/dlm/dlmdebug.c~ocfs2-dlm-fix-race-between-convert-and-recovery-v3 +++ a/fs/ocfs2/dlm/dlmdebug.c @@ -77,7 +77,7 @@ static void __dlm_print_lock(struct dlm_ printk(" type=%d, conv=%d, node=%u, cookie=%u:%llu, " "ref=%u, ast=(empty=%c,pend=%c), bast=(empty=%c,pend=%c), " - "pending=(lock=%c,cancel=%c,unlock=%c)\n", + "pending=(conv=%c,lock=%c,cancel=%c,unlock=%c)\n", lock->ml.type, lock->ml.convert_type, lock->ml.node, dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)), dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)), @@ -86,6 +86,7 @@ static void __dlm_print_lock(struct dlm_ (lock->ast_pending ? 'y' : 'n'), (list_empty(&lock->bast_list) ? 'y' : 'n'), (lock->bast_pending ? 'y' : 'n'), + (lock->convert_pending ? 'y' : 'n'), (lock->lock_pending ? 'y' : 'n'), (lock->cancel_pending ? 'y' : 'n'), (lock->unlock_pending ? 'y' : 'n')); @@ -501,7 +502,7 @@ static int dump_lock(struct dlm_lock *lo #define DEBUG_LOCK_VERSION 1 spin_lock(&lock->spinlock); - out = snprintf(buf, len, "LOCK:%d,%d,%d,%d,%d,%d:%lld,%d,%d,%d,%d," + out = snprintf(buf, len, "LOCK:%d,%d,%d,%d,%d,%d:%lld,%d,%d,%d,%d,%d," "%d,%d,%d,%d\n", DEBUG_LOCK_VERSION, list_type, lock->ml.type, lock->ml.convert_type, @@ -511,7 +512,7 @@ static int dump_lock(struct dlm_lock *lo !list_empty(&lock->ast_list), !list_empty(&lock->bast_list), lock->ast_pending, lock->bast_pending, - lock->lock_pending, + lock->convert_pending, lock->lock_pending, lock->cancel_pending, lock->unlock_pending, atomic_read(&lock->lock_refs.refcount)); spin_unlock(&lock->spinlock); diff -puN fs/ocfs2/dlm/dlmlock.c~ocfs2-dlm-fix-race-between-convert-and-recovery-v3 fs/ocfs2/dlm/dlmlock.c --- a/fs/ocfs2/dlm/dlmlock.c~ocfs2-dlm-fix-race-between-convert-and-recovery-v3 +++ a/fs/ocfs2/dlm/dlmlock.c @@ -411,6 +411,7 @@ static void dlm_init_lock(struct dlm_loc newlock->ml.cookie = cpu_to_be64(cookie); newlock->ast_pending = 0; newlock->bast_pending = 0; + newlock->convert_pending = 0; newlock->lock_pending = 0; newlock->unlock_pending = 0; newlock->cancel_pending = 0; diff -puN fs/ocfs2/dlm/dlmrecovery.c~ocfs2-dlm-fix-race-between-convert-and-recovery-v3 fs/ocfs2/dlm/dlmrecovery.c --- a/fs/ocfs2/dlm/dlmrecovery.c~ocfs2-dlm-fix-race-between-convert-and-recovery-v3 +++ a/fs/ocfs2/dlm/dlmrecovery.c @@ -2081,7 +2081,15 @@ void dlm_move_lockres_to_recovery_list(s queue = dlm_list_idx_to_ptr(res, i); list_for_each_entry_safe(lock, next, queue, list) { dlm_lock_get(lock); - if (lock->lock_pending) { + if (lock->convert_pending) { + /* move converting lock back to granted */ + BUG_ON(i != DLM_CONVERTING_LIST); + mlog(0, "node died with convert pending " + "on %.*s. move back to granted list.\n", + res->lockname.len, res->lockname.name); + dlm_revert_pending_convert(res, lock); + lock->convert_pending = 0; + } else if (lock->lock_pending) { /* remove pending lock requests completely */ BUG_ON(i != DLM_BLOCKED_LIST); mlog(0, "node died with lock pending " _ Patches currently in -mm which might be from joseph.qi@xxxxxxxxxx are ocfs2-dlm-fix-race-between-convert-and-recovery.patch ocfs2-dlm-fix-bug-in-dlm_move_lockres_to_recovery_list.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html