From e16ffa838b2060dd4025125dffd2f83b9d9d6b43 Mon Sep 17 00:00:00 2001 From: Niu Yawei Date: Wed, 26 Jul 2017 11:22:25 -0400 Subject: [PATCH] staging: lustre: ptlrpc: no need to reassign mbits for replay It's not necessary reassgin & re-adjust rq_mbits for replay request in ptlrpc_set_bulk_mbits(), they all must have already been correctly assigned before. Such unecessary reassign could make the first matchbit not PTLRPC_BULK_OPS_MASK aligned, that'll trigger LASSERT in ptlrpc_register_bulk(): - ptlrpc_set_bulk_mbits() is called when first time sending request, rq_mbits is set as xid, which is BULK_OPS aligned; - ptlrpc_set_bulk_mbits() continue to adjust the mbits for multi-bulk RPC, rq_mbits is not aligned anymore, then rq_xid is changed accordingly if client is connecting to an old server, so rq_xid became unaligned too; - The request is replayed, ptlrpc_set_bulk_mbits() reassign the rq_mbits as rq_xid, which isn't aligned already, but ptlrpc_register_bulk() still assumes this value as the first matchbits and LASSERT it's BULK_OPS aligned. Signed-off-by: Niu Yawei Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6808 Reviewed-on: http://review.whamcloud.com/23048 Reviewed-by: Fan Yong Reviewed-by: Alex Zhuravlev Reviewed-by: Oleg Drokin Signed-off-by: James Simmons Signed-off-by: Greg Kroah-Hartman --- drivers/staging/lustre/lustre/ptlrpc/client.c | 28 +++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/drivers/staging/lustre/lustre/ptlrpc/client.c b/drivers/staging/lustre/lustre/ptlrpc/client.c index 1c77792..1247686 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/client.c +++ b/drivers/staging/lustre/lustre/ptlrpc/client.c @@ -3116,13 +3116,20 @@ void ptlrpc_set_bulk_mbits(struct ptlrpc_request *req) LASSERT(bd); - if (!req->rq_resend) { - /* this request has a new xid, just use it as bulk matchbits */ - req->rq_mbits = req->rq_xid; - - } else { /* needs to generate a new matchbits for resend */ + /* + * Generate new matchbits for all resend requests, including + * resend replay. + */ + if (req->rq_resend) { u64 old_mbits = req->rq_mbits; + /* + * First time resend on -EINPROGRESS will generate new xid, + * so we can actually use the rq_xid as rq_mbits in such case, + * however, it's bit hard to distinguish such resend with a + * 'resend for the -EINPROGRESS resend'. To make it simple, + * we opt to generate mbits for all resend cases. + */ if ((bd->bd_import->imp_connect_data.ocd_connect_flags & OBD_CONNECT_BULK_MBITS)) { req->rq_mbits = ptlrpc_next_xid(); @@ -3131,12 +3138,21 @@ void ptlrpc_set_bulk_mbits(struct ptlrpc_request *req) spin_lock(&req->rq_import->imp_lock); list_del_init(&req->rq_unreplied_list); ptlrpc_assign_next_xid_nolock(req); - req->rq_mbits = req->rq_xid; spin_unlock(&req->rq_import->imp_lock); + req->rq_mbits = req->rq_xid; } CDEBUG(D_HA, "resend bulk old x%llu new x%llu\n", old_mbits, req->rq_mbits); + } else if (!(lustre_msg_get_flags(req->rq_reqmsg) & MSG_REPLAY)) { + /* Request being sent first time, use xid as matchbits. */ + req->rq_mbits = req->rq_xid; + } else { + /* + * Replay request, xid and matchbits have already been + * correctly assigned. + */ + return; } /* -- 2.7.4