From patchwork Mon Feb 23 18:00:34 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Christoph Hellwig X-Patchwork-Id: 5867571 Return-Path: X-Original-To: patchwork-linux-fsdevel@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id E44619F169 for ; Mon, 23 Feb 2015 18:03:07 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id D485620639 for ; Mon, 23 Feb 2015 18:03:06 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 8CEB720465 for ; Mon, 23 Feb 2015 18:03:05 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752566AbbBWSDE (ORCPT ); Mon, 23 Feb 2015 13:03:04 -0500 Received: from bombadil.infradead.org ([198.137.202.9]:54889 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752559AbbBWSDC (ORCPT ); Mon, 23 Feb 2015 13:03:02 -0500 Received: from bombadil.infradead.org ([2001:1868:205::9] helo=localhost) by bombadil.infradead.org with esmtpsa (Exim 4.80.1 #2 (Red Hat Linux)) id 1YPxLJ-0006Yo-C9; Mon, 23 Feb 2015 18:02:53 +0000 From: Christoph Hellwig To: Al Viro Cc: Maxim Patlasov , Robert Baldyga , Michal Nazarewicz , Felipe Balbi , linux-aio@kvack.org, linux-fsdevel@vger.kernel.org Subject: [PATCH 10/12] fs: don't allow to complete sync iocbs through aio_complete Date: Mon, 23 Feb 2015 10:00:34 -0800 Message-Id: <1424714436-19371-11-git-send-email-hch@lst.de> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1424714436-19371-1-git-send-email-hch@lst.de> References: <1424714436-19371-1-git-send-email-hch@lst.de> X-SRS-Rewrite: SMTP reverse-path rewritten from by bombadil.infradead.org See http://www.infradead.org/rpr.html Sender: linux-fsdevel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, T_RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP The AIO interface is fairly complex because it tries to allow filesystems to always work async and then wakeup a synchronous caller through aio_complete. It turns out that basically no one was doing this to avoid the complexity and context switches, and we've already fixed up the remaining users and can now get rid of this case. Signed-off-by: Christoph Hellwig --- fs/aio.c | 24 +----------------------- fs/ecryptfs/file.c | 6 ------ fs/read_write.c | 26 ++++++++------------------ include/linux/aio.h | 4 ---- net/socket.c | 9 +++------ 5 files changed, 12 insertions(+), 57 deletions(-) diff --git a/fs/aio.c b/fs/aio.c index 667054c..8ca8df1 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -778,22 +778,6 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, return 0; } -/* wait_on_sync_kiocb: - * Waits on the given sync kiocb to complete. - */ -ssize_t wait_on_sync_kiocb(struct kiocb *req) -{ - while (!req->ki_ctx) { - set_current_state(TASK_UNINTERRUPTIBLE); - if (req->ki_ctx) - break; - io_schedule(); - } - __set_current_state(TASK_RUNNING); - return req->ki_user_data; -} -EXPORT_SYMBOL(wait_on_sync_kiocb); - /* * exit_aio: called when the last user of mm goes away. At this point, there is * no way for any new requests to be submited or any of the io_* syscalls to be @@ -1025,13 +1009,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) * ref, no other paths have a way to get another ref * - the sync task helpfully left a reference to itself in the iocb */ - if (is_sync_kiocb(iocb)) { - iocb->ki_user_data = res; - smp_wmb(); - iocb->ki_ctx = ERR_PTR(-EXDEV); - wake_up_process(iocb->ki_obj.tsk); - return; - } + BUG_ON(is_sync_kiocb(iocb)); if (iocb->ki_list.next) { unsigned long flags; diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 6f4e659..a36da88 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -52,12 +52,6 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb, struct file *file = iocb->ki_filp; rc = generic_file_read_iter(iocb, to); - /* - * Even though this is a async interface, we need to wait - * for IO to finish to update atime - */ - if (-EIOCBQUEUED == rc) - rc = wait_on_sync_kiocb(iocb); if (rc >= 0) { path = ecryptfs_dentry_to_lower_path(file->f_path.dentry); touch_atime(path); diff --git a/fs/read_write.c b/fs/read_write.c index f8b8fc1..76e324e 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -346,9 +346,7 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos) iter->type |= READ; ret = file->f_op->read_iter(&kiocb, iter); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); - + BUG_ON(ret == -EIOCBQUEUED); if (ret > 0) *ppos = kiocb.ki_pos; return ret; @@ -368,9 +366,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos) iter->type |= WRITE; ret = file->f_op->write_iter(&kiocb, iter); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); - + BUG_ON(ret == -EIOCBQUEUED); if (ret > 0) *ppos = kiocb.ki_pos; return ret; @@ -426,8 +422,7 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp kiocb.ki_pos = *ppos; ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } @@ -446,8 +441,7 @@ ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *p iov_iter_init(&iter, READ, &iov, 1, len); ret = filp->f_op->read_iter(&kiocb, &iter); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } @@ -508,8 +502,7 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof kiocb.ki_pos = *ppos; ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } @@ -528,8 +521,7 @@ ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, lo iov_iter_init(&iter, WRITE, &iov, 1, len); ret = filp->f_op->write_iter(&kiocb, &iter); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } @@ -716,8 +708,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, int rw, const struct iove iov_iter_init(&iter, rw, iov, nr_segs, len); ret = fn(&kiocb, &iter); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } @@ -732,8 +723,7 @@ static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, kiocb.ki_pos = *ppos; ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); + BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; } diff --git a/include/linux/aio.h b/include/linux/aio.h index 132d1ec..f851643 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -37,7 +37,6 @@ struct kiocb { union { void __user *user; - struct task_struct *tsk; } ki_obj; __u64 ki_user_data; /* user's data for completion */ @@ -63,13 +62,11 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) *kiocb = (struct kiocb) { .ki_ctx = NULL, .ki_filp = filp, - .ki_obj.tsk = current, }; } /* prototypes */ #ifdef CONFIG_AIO -extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); extern void aio_complete(struct kiocb *iocb, long res, long res2); struct mm_struct; extern void exit_aio(struct mm_struct *mm); @@ -77,7 +74,6 @@ extern long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user *__user *iocbpp, bool compat); void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel); #else -static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } static inline void aio_complete(struct kiocb *iocb, long res, long res2) { } struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } diff --git a/net/socket.c b/net/socket.c index f921455..f6c519d 100644 --- a/net/socket.c +++ b/net/socket.c @@ -633,8 +633,7 @@ static int do_sock_sendmsg(struct socket *sock, struct msghdr *msg, init_sync_kiocb(&iocb, NULL); ret = nosec ? __sock_sendmsg_nosec(&iocb, sock, msg, size) : __sock_sendmsg(&iocb, sock, msg, size); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); + BUG_ON(ret == -EIOCBQUEUED); return ret; } @@ -766,8 +765,7 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg, init_sync_kiocb(&iocb, NULL); ret = __sock_recvmsg(&iocb, sock, msg, size, flags); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); + BUG_ON(ret == -EIOCBQUEUED); return ret; } EXPORT_SYMBOL(sock_recvmsg); @@ -780,8 +778,7 @@ static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, init_sync_kiocb(&iocb, NULL); ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&iocb); + BUG_ON(ret == -EIOCBQUEUED); return ret; }