From patchwork Thu Apr 6 11:23:20 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Benjamin Coddington X-Patchwork-Id: 9666887 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 2A69360364 for ; Thu, 6 Apr 2017 11:23:34 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 26F332832D for ; Thu, 6 Apr 2017 11:23:34 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 1A13928354; Thu, 6 Apr 2017 11:23:34 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 97E162832D for ; Thu, 6 Apr 2017 11:23:33 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754854AbdDFLXb (ORCPT ); Thu, 6 Apr 2017 07:23:31 -0400 Received: from mx1.redhat.com ([209.132.183.28]:45084 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754447AbdDFLXZ (ORCPT ); Thu, 6 Apr 2017 07:23:25 -0400 Received: from int-mx14.intmail.prod.int.phx2.redhat.com (int-mx14.intmail.prod.int.phx2.redhat.com [10.5.11.27]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id DB095C0467CB; Thu, 6 Apr 2017 11:23:24 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mx1.redhat.com DB095C0467CB Authentication-Results: ext-mx07.extmail.prod.ext.phx2.redhat.com; dmarc=none (p=none dis=none) header.from=redhat.com Authentication-Results: ext-mx07.extmail.prod.ext.phx2.redhat.com; spf=pass smtp.mailfrom=bcodding@redhat.com DKIM-Filter: OpenDKIM Filter v2.11.0 mx1.redhat.com DB095C0467CB Received: from bcodding.csb (ovpn-117-66.phx2.redhat.com [10.3.117.66]) by int-mx14.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id v36BNNwA026060; Thu, 6 Apr 2017 07:23:24 -0400 Received: by bcodding.csb (Postfix, from userid 24008) id 1FD2410C3119; Thu, 6 Apr 2017 07:23:22 -0400 (EDT) From: Benjamin Coddington To: Trond Myklebust , Anna Schumaker , Jeff Layton , bfields@fieldses.org, Miklos Szeredi , Alexander Viro Cc: linux-nfs@vger.kernel.org, linux-fsdevel@vger.kernel.org Subject: [PATCH 4/6] NFS: Add an iocounter wait function for async RPC tasks Date: Thu, 6 Apr 2017 07:23:20 -0400 Message-Id: In-Reply-To: References: In-Reply-To: References: X-Scanned-By: MIMEDefang 2.68 on 10.5.11.27 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.31]); Thu, 06 Apr 2017 11:23:25 +0000 (UTC) Sender: linux-nfs-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-nfs@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP By sleeping on a new NFS Unlock-On-Close waitqueue, rpc tasks may wait for a lock context's iocounter to reach zero. The rpc waitqueue is only woken when the open_context has the NFS_CONTEXT_UNLOCK flag set in order to mitigate spurious wake-ups for any iocounter reaching zero. Signed-off-by: Benjamin Coddington Reviewed-by: Jeff Layton --- fs/nfs/client.c | 1 + fs/nfs/pagelist.c | 26 +++++++++++++++++++++++++- include/linux/nfs_fs.h | 1 + include/linux/nfs_fs_sb.h | 1 + include/linux/nfs_page.h | 1 + 5 files changed, 29 insertions(+), 1 deletion(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 91a8d610ba0f..c335c6dce285 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -218,6 +218,7 @@ static void nfs_cb_idr_remove_locked(struct nfs_client *clp) static void pnfs_init_server(struct nfs_server *server) { rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC"); + rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC"); } #else diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 6e629b856a00..d163819e4416 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -115,6 +115,27 @@ nfs_iocounter_wait(struct nfs_lock_context *l_ctx) TASK_KILLABLE); } +bool +nfs_async_iocounter_wait(struct rpc_task *task, void *data) +{ + struct nfs_lock_context *l_ctx = data; + struct inode *inode = d_inode(l_ctx->open_context->dentry); + bool ret = false; + + if (atomic_read(&l_ctx->io_count) > 0) { + rpc_sleep_on(&NFS_SERVER(inode)->uoc_rpcwaitq, task, NULL); + ret = true; + } + + if (atomic_read(&l_ctx->io_count) == 0) { + rpc_wake_up_queued_task(&NFS_SERVER(inode)->uoc_rpcwaitq, task); + ret = false; + } + + return ret; +} +EXPORT_SYMBOL_GPL(nfs_async_iocounter_wait); + /* * nfs_page_group_lock - lock the head of the page group * @req - request in group that is to be locked @@ -398,8 +419,11 @@ static void nfs_clear_request(struct nfs_page *req) req->wb_page = NULL; } if (l_ctx != NULL) { - if (atomic_dec_and_test(&l_ctx->io_count)) + if (atomic_dec_and_test(&l_ctx->io_count)) { wake_up_atomic_t(&l_ctx->io_count); + if (test_bit(NFS_CONTEXT_UNLOCK, &ctx->flags)) + rpc_wake_up(&NFS_SERVER(d_inode(ctx->dentry))->uoc_rpcwaitq); + } nfs_put_lock_context(l_ctx); req->wb_lock_context = NULL; } diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f1da8c8dd473..3ce3e42beead 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -76,6 +76,7 @@ struct nfs_open_context { #define NFS_CONTEXT_ERROR_WRITE (0) #define NFS_CONTEXT_RESEND_WRITES (1) #define NFS_CONTEXT_BAD (2) +#define NFS_CONTEXT_UNLOCK (3) int error; struct list_head list; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index b34097c67848..2a70f34dffe8 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -222,6 +222,7 @@ struct nfs_server { u32 mountd_version; unsigned short mountd_port; unsigned short mountd_protocol; + struct rpc_wait_queue uoc_rpcwaitq; }; /* Server capabilities */ diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 957049f72290..d39ebcba52c8 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -141,6 +141,7 @@ extern int nfs_page_group_lock(struct nfs_page *, bool); extern void nfs_page_group_lock_wait(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); +extern bool nfs_async_iocounter_wait(struct rpc_task *, void *); /* * Lock the page of an asynchronous request