From 2d097e5f5c039618a49a37f7ee457bc4e5f48d1d Mon Sep 17 00:00:00 2001 From: Alexander Boyko Date: Sat, 7 Oct 2017 22:37:48 +0000 Subject: [PATCH] staging: lustre: ptlrpc: skip lock if export failed [ Upstream commit 4c43c27ddc461d8473cedd70f2549614641dfbc7 ] This patch resolves IO vs eviction race. After eviction failed export stayed at stale list, a client had IO processing and reconnected during it. A client sent brw rpc with last lock cookie and new connection. The lock with failed export was found and assert was happened. (ost_handler.c:1812:ost_prolong_lock_one()) ASSERTION( lock->l_export == opd->opd_exp ) failed: 1. Skip the lock at ldlm_handle2lock if lock export failed. 2. Validation of lock for IO was added at hpreq_check(). The lock searching is based on granted interval tree. If server doesn`t have a valid lock, it reply to client with ESTALE. Signed-off-by: Alexander Boyko Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-7702 Seagate-bug-id: MRP-2787 Reviewed-on: http://review.whamcloud.com/18120 Reviewed-by: Fan Yong Reviewed-by: Vitaly Fertman Reviewed-by: Oleg Drokin Signed-off-by: James Simmons Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- .../staging/lustre/lustre/ldlm/ldlm_lock.c | 7 +++++++ .../staging/lustre/lustre/ptlrpc/service.c | 21 +++++++------------ 2 files changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_lock.c b/drivers/staging/lustre/lustre/ldlm/ldlm_lock.c index 7f8c70056ffd..040553d6e316 100644 --- a/drivers/staging/lustre/lustre/ldlm/ldlm_lock.c +++ b/drivers/staging/lustre/lustre/ldlm/ldlm_lock.c @@ -550,6 +550,13 @@ struct ldlm_lock *__ldlm_handle2lock(const struct lustre_handle *handle, if (lock == NULL) return NULL; + if (lock->l_export && lock->l_export->exp_failed) { + CDEBUG(D_INFO, "lock export failed: lock %p, exp %p\n", + lock, lock->l_export); + LDLM_LOCK_PUT(lock); + return NULL; + } + /* It's unlikely but possible that someone marked the lock as * destroyed after we did handle2object on it */ if (flags == 0 && ((lock->l_flags & LDLM_FL_DESTROYED) == 0)) { diff --git a/drivers/staging/lustre/lustre/ptlrpc/service.c b/drivers/staging/lustre/lustre/ptlrpc/service.c index f45898f17793..6d3c25ccb297 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/service.c +++ b/drivers/staging/lustre/lustre/ptlrpc/service.c @@ -1240,20 +1240,15 @@ static int ptlrpc_server_hpreq_init(struct ptlrpc_service_part *svcpt, * it may hit swab race at LU-1044. */ if (req->rq_ops->hpreq_check) { rc = req->rq_ops->hpreq_check(req); - /** - * XXX: Out of all current - * ptlrpc_hpreq_ops::hpreq_check(), only - * ldlm_cancel_hpreq_check() can return an error code; - * other functions assert in similar places, which seems - * odd. What also does not seem right is that handlers - * for those RPCs do not assert on the same checks, but - * rather handle the error cases. e.g. see - * ost_rw_hpreq_check(), and ost_brw_read(), - * ost_brw_write(). + if (rc == -ESTALE) { + req->rq_status = rc; + ptlrpc_error(req); + } + /** can only return error, + * 0 for normal request, + * or 1 for high priority request */ - if (rc < 0) - return rc; - LASSERT(rc == 0 || rc == 1); + LASSERT(rc <= 1); } spin_lock_bh(&req->rq_export->exp_rpc_lock); -- 2.20.1