From patchwork Mon Jul 24 22:55:04 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13325422 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8C378C001DE for ; Mon, 24 Jul 2023 22:55:20 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229659AbjGXWzT (ORCPT ); Mon, 24 Jul 2023 18:55:19 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33422 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229848AbjGXWzS (ORCPT ); Mon, 24 Jul 2023 18:55:18 -0400 Received: from mail-pl1-x630.google.com (mail-pl1-x630.google.com [IPv6:2607:f8b0:4864:20::630]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 3282FE5A for ; Mon, 24 Jul 2023 15:55:17 -0700 (PDT) Received: by mail-pl1-x630.google.com with SMTP id d9443c01a7336-1bbadf9ed37so1478665ad.0 for ; Mon, 24 Jul 2023 15:55:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20221208.gappssmtp.com; s=20221208; t=1690239316; x=1690844116; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=A/R5UlJihGOa6+mEJqx8lHR7UM+4ST5J1wIdWJwVmsw=; b=Z4eRb4Fg/xOnz5US0iHTMZBP+UrWEINLRqVJiwIiQi93n/tGr8LMLJ/dLP9suWM6Vc H3R6uihOBZu+zqp0XHp7ZojMRFSEEebl65nWOjnpr87DSi19vDBEabDIGH1LseWpNxxW h9vWvqKHN1wm+O7wX8/EwV+2h1MLvdu6LEFk8NE42dpYCbwGYO/Uln6J67rhbhwK4NcB EoPwQF7DJFTHlRxM8ge98xdW6DLAiYpRWB7peB6narKkDKCEMvJUaoaV1JBycx57pXop n/zCosM6xzHK2S9yv2F4TEtP6qlzNxZPrY3h6wD8BE4hYCRcJh6GdOXKs30/oW1K8D9k en8A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1690239316; x=1690844116; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=A/R5UlJihGOa6+mEJqx8lHR7UM+4ST5J1wIdWJwVmsw=; b=H1yvz2d1zrz192Tk55rcCdAC3MRRgKukOaQqiB6Z+3Zacupr2aA+6R+uhYUu6DZ1yO rueMgfOvvl1yY86amucGkwfJeGik81SJ0+1tj6s2LEWNxEeq+3qgveJfqh8h+q9a22mo 4b3tMCClUWfV49FRbOVmT1SAFKi7C6ELUrJLfcT62as9nxsdOsmQGI2xC3VKXzecvLlO jHNHwMznfVDfGKtYL5bnGQfGY/QBKfQcSEt+bfaJaj/sR+4b2ZceRAFsj4Bw7BlEK7jT l128sB4pXLtIxNacXicS7k1+h2fX/9xT85IB66udiX9wwNSYVqH+hSDKF+tSdCiRPiFH ATOQ== X-Gm-Message-State: ABy/qLaHfDbGopX1T4M9egNdXRiUJp35DSH5sTr5lqyURUjJb2DjqtTp Jyh4NztkaktaTFpPBPnlnLi8RqAUWkDm0ZcC214= X-Google-Smtp-Source: APBJJlFmb5w7Cf5UsiJZA1gyKD5FHUU0imdizY6mcFZDEw4ad1e0VV2drsmrNPcbUJTLy5v1L2O9sA== X-Received: by 2002:a17:903:41cd:b0:1bb:9e6e:a9f3 with SMTP id u13-20020a17090341cd00b001bb9e6ea9f3mr6381477ple.4.1690239316678; Mon, 24 Jul 2023 15:55:16 -0700 (PDT) Received: from localhost.localdomain ([198.8.77.157]) by smtp.gmail.com with ESMTPSA id p7-20020a1709026b8700b001acae9734c0sm9424733plk.266.2023.07.24.15.55.15 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 24 Jul 2023 15:55:16 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org, linux-xfs@vger.kernel.org Cc: hch@lst.de, andres@anarazel.de, david@fromorbit.com, djwong@kernel.org, Jens Axboe Subject: [PATCH 1/8] iomap: cleanup up iomap_dio_bio_end_io() Date: Mon, 24 Jul 2023 16:55:04 -0600 Message-Id: <20230724225511.599870-2-axboe@kernel.dk> X-Mailer: git-send-email 2.40.1 In-Reply-To: <20230724225511.599870-1-axboe@kernel.dk> References: <20230724225511.599870-1-axboe@kernel.dk> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-xfs@vger.kernel.org Make the logic a bit easier to follow: 1) Add a release_bio out path, as everybody needs to touch that, and have our bio ref check jump there if it's non-zero. 2) Add a kiocb local variable. 3) Add comments for each of the three conditions (sync, inline, or async workqueue punt). No functional changes in this patch. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/iomap/direct-io.c | 46 +++++++++++++++++++++++++++++--------------- 1 file changed, 31 insertions(+), 15 deletions(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index ea3b868c8355..0ce60e80c901 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -152,27 +152,43 @@ void iomap_dio_bio_end_io(struct bio *bio) { struct iomap_dio *dio = bio->bi_private; bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY); + struct kiocb *iocb = dio->iocb; if (bio->bi_status) iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status)); + if (!atomic_dec_and_test(&dio->ref)) + goto release_bio; - if (atomic_dec_and_test(&dio->ref)) { - if (dio->wait_for_completion) { - struct task_struct *waiter = dio->submit.waiter; - WRITE_ONCE(dio->submit.waiter, NULL); - blk_wake_io_task(waiter); - } else if (dio->flags & IOMAP_DIO_WRITE) { - struct inode *inode = file_inode(dio->iocb->ki_filp); - - WRITE_ONCE(dio->iocb->private, NULL); - INIT_WORK(&dio->aio.work, iomap_dio_complete_work); - queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work); - } else { - WRITE_ONCE(dio->iocb->private, NULL); - iomap_dio_complete_work(&dio->aio.work); - } + /* + * Synchronous dio, task itself will handle any completion work + * that needs after IO. All we need to do is wake the task. + */ + if (dio->wait_for_completion) { + struct task_struct *waiter = dio->submit.waiter; + + WRITE_ONCE(dio->submit.waiter, NULL); + blk_wake_io_task(waiter); + goto release_bio; + } + + /* Read completion can always complete inline. */ + if (!(dio->flags & IOMAP_DIO_WRITE)) { + WRITE_ONCE(iocb->private, NULL); + iomap_dio_complete_work(&dio->aio.work); + goto release_bio; } + /* + * Async DIO completion that requires filesystem level completion work + * gets punted to a work queue to complete as the operation may require + * more IO to be issued to finalise filesystem metadata changes or + * guarantee data integrity. + */ + WRITE_ONCE(iocb->private, NULL); + INIT_WORK(&dio->aio.work, iomap_dio_complete_work); + queue_work(file_inode(iocb->ki_filp)->i_sb->s_dio_done_wq, + &dio->aio.work); +release_bio: if (should_dirty) { bio_check_pages_dirty(bio); } else { From patchwork Mon Jul 24 22:55:05 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13325421 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 34166C04A94 for ; Mon, 24 Jul 2023 22:55:21 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230084AbjGXWzU (ORCPT ); Mon, 24 Jul 2023 18:55:20 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33434 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230062AbjGXWzT (ORCPT ); Mon, 24 Jul 2023 18:55:19 -0400 Received: from mail-pl1-x62c.google.com (mail-pl1-x62c.google.com [IPv6:2607:f8b0:4864:20::62c]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 45C59100 for ; Mon, 24 Jul 2023 15:55:18 -0700 (PDT) Received: by mail-pl1-x62c.google.com with SMTP id d9443c01a7336-1bba9539a23so1825845ad.1 for ; Mon, 24 Jul 2023 15:55:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20221208.gappssmtp.com; s=20221208; t=1690239318; x=1690844118; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=eVeLYS33nnc1708rDqfbQibRM29ZHSZOxWFzkowQIMY=; b=ykm9gWdurj0xOxNjjFoGt7mW+OF9Gw/mBBQYDdfmgAR63NziZCw7JWsImTNuRnwqQo Wa1aZQ8/c6v82ktiGrh8sftd+3evkOvwVSYT8EuHB0ykswG2vdvFhgDu67fczpcRPwmn DRFxhrtpDi+H7zZy0A5D0sjP93cQYLEZE4vhxnhA/7bDs1VI2cayrOp5LJdJN4v2f5Rt /j/RKgIBYDUYcz+Wa8NLZcr39bRM/paQtfR6K2cNHC/QiYD/u6s6Uk6dr4CIiIeEwFSI DgBH9UNr3jaCGYG61cc8CciPApi+Q7wQJOCJ0SdmTPBHxayNs9nRH6rM51+6gYeaxbJM gn9w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1690239318; x=1690844118; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=eVeLYS33nnc1708rDqfbQibRM29ZHSZOxWFzkowQIMY=; b=jgy3/7zhNfoaJ44TSgHC+2CVrs2CeXnnj+lHaSZmWMpKeVSJq61dfVfW0Q/lNxxSGP buMyl7B/VVbsm4bzFHcayrieKdEWbrtonpFPrb5vbtvmkNYDXmEdCEePCkuLjAeh+c8G 7Rwrr3jnBQzce+U3SI4sCraH1CLWoKZnGtAoq3kOoe0yaUQV9pZ6S/Oyftrc3WIQkN4C kfnt9dAmysAzjPb1MdlUaUx+EA0mW/bgCz1EpFmowda4vIrJH1kPBkyFZSxBFILI12cp o2f6YRFMQNNnYAMu/Qeo9vfX4l7JlzA0FpD+7JkUDW3ejqI00h9EpqcgIEIJ2J32qt1o q/bw== X-Gm-Message-State: ABy/qLamfG82pP+NBowN/QC0aZ/PBXQr27Nd3OiMYdWfNx3bHFNuMevV YBA+meqOA8rdkPqWlNJetmB3pg== X-Google-Smtp-Source: APBJJlGftuzyUY14869rqyzSOwXATOafJNKRe47t9tts3Omzk/El6tbEHeyUXO9Zpn43CHB8fY3Tlg== X-Received: by 2002:a17:902:dad2:b0:1b8:9fc4:2733 with SMTP id q18-20020a170902dad200b001b89fc42733mr14708729plx.3.1690239317766; Mon, 24 Jul 2023 15:55:17 -0700 (PDT) Received: from localhost.localdomain ([198.8.77.157]) by smtp.gmail.com with ESMTPSA id p7-20020a1709026b8700b001acae9734c0sm9424733plk.266.2023.07.24.15.55.16 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 24 Jul 2023 15:55:17 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org, linux-xfs@vger.kernel.org Cc: hch@lst.de, andres@anarazel.de, david@fromorbit.com, djwong@kernel.org, Jens Axboe Subject: [PATCH 2/8] iomap: use an unsigned type for IOMAP_DIO_* defines Date: Mon, 24 Jul 2023 16:55:05 -0600 Message-Id: <20230724225511.599870-3-axboe@kernel.dk> X-Mailer: git-send-email 2.40.1 In-Reply-To: <20230724225511.599870-1-axboe@kernel.dk> References: <20230724225511.599870-1-axboe@kernel.dk> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-xfs@vger.kernel.org IOMAP_DIO_DIRTY shifts by 31 bits, which makes UBSAN unhappy. Clean up all the defines by making the shifted value an unsigned value. Reviewed-by: Darrick J. Wong Reported-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/iomap/direct-io.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 0ce60e80c901..7d627d43d10b 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -20,10 +20,10 @@ * Private flags for iomap_dio, must not overlap with the public ones in * iomap.h: */ -#define IOMAP_DIO_WRITE_FUA (1 << 28) -#define IOMAP_DIO_NEED_SYNC (1 << 29) -#define IOMAP_DIO_WRITE (1 << 30) -#define IOMAP_DIO_DIRTY (1 << 31) +#define IOMAP_DIO_WRITE_FUA (1U << 28) +#define IOMAP_DIO_NEED_SYNC (1U << 29) +#define IOMAP_DIO_WRITE (1U << 30) +#define IOMAP_DIO_DIRTY (1U << 31) struct iomap_dio { struct kiocb *iocb; From patchwork Mon Jul 24 22:55:06 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13325423 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2CD85C04A6A for ; Mon, 24 Jul 2023 22:55:22 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230141AbjGXWzU (ORCPT ); Mon, 24 Jul 2023 18:55:20 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33452 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229496AbjGXWzU (ORCPT ); Mon, 24 Jul 2023 18:55:20 -0400 Received: from mail-pl1-x632.google.com (mail-pl1-x632.google.com [IPv6:2607:f8b0:4864:20::632]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 34DC0E5A for ; Mon, 24 Jul 2023 15:55:19 -0700 (PDT) Received: by mail-pl1-x632.google.com with SMTP id d9443c01a7336-1bbadf9ed37so1478725ad.0 for ; Mon, 24 Jul 2023 15:55:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20221208.gappssmtp.com; s=20221208; t=1690239318; x=1690844118; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=Wx3gDejnv+MYuO8cUn67Qw106/rsCHumB4kwemSJRZY=; b=bm+YKX6D1BwkR4vrs42vdWoeqGRLlquEzDtbB0b00LKREL0LWQEHHMtZV+Lve3k79k nJlObut1EZppwPrHtzilkZnngV2wP5bNloU+coVqsuEOL/nmSD5mM5mVyfZeCs0KdGrc eUjDg+Mswj6k7ivu7z7L/9wxEMuwiEJoztbGAfmnGDVcsfkIIXcDMR+CB0aT5Fb3WpO0 qaS049XZo1myuKfEwG+guOIHssrbJ1NhrfOxOG3Kyrt8JeE64/L+kHziZl6wDN70GdmX P92zM73IY4gVZwhJJBo4VQCBKTWrSEt9KqfghLeUxNDlFBApp8YNLhVNxJA/StUHYMAp px6A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1690239318; x=1690844118; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=Wx3gDejnv+MYuO8cUn67Qw106/rsCHumB4kwemSJRZY=; b=T4+sPsiG84QqypDQ23YN7SA05tDW/TDa7ao5O7YBFlxnPrFoHvQCAgXI2SvgzFDZa7 LEqX0nLIrQZezspVrn3ONSwRHf3ATyngMQ0n1DlAFx5hMECyarXFREzZ3rHWlC3SDzZA j6RL6lA7XKPz/bZW/lTyYnf5N9nxkC7oQshpC54uAUJlpG9ZOTEZ7oUASolmL0fD6gio X5Ipqewq+zKUpWjgbO5/bzECWCB2aJHzDCVDCkps3agYXXMxJpFgDwO3FnTMMn10IN3b ssooM2ETtDKkrcEuiAUkjeI4WJs2edwgIbzT2kAJVfo6uLw/dKeOSJwT1FbvpYYtqMJc Pxfw== X-Gm-Message-State: ABy/qLbfmukuXp6vFUjQToyO6lGN+cFGLnVWRKlFlISbVeQVDqXknxfe 1XXsi3dHtdgHoS/oCDIquMwQSw== X-Google-Smtp-Source: APBJJlHvNGqZ/QpFqqw+CFa53OAtegzHdOldV4x76K1a9aUXPkJY8NVWbAeVvyGXes1jwAY4Frt8tw== X-Received: by 2002:a17:902:e74d:b0:1bb:ac37:384b with SMTP id p13-20020a170902e74d00b001bbac37384bmr3491050plf.6.1690239318701; Mon, 24 Jul 2023 15:55:18 -0700 (PDT) Received: from localhost.localdomain ([198.8.77.157]) by smtp.gmail.com with ESMTPSA id p7-20020a1709026b8700b001acae9734c0sm9424733plk.266.2023.07.24.15.55.17 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 24 Jul 2023 15:55:18 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org, linux-xfs@vger.kernel.org Cc: hch@lst.de, andres@anarazel.de, david@fromorbit.com, djwong@kernel.org, Jens Axboe Subject: [PATCH 3/8] iomap: treat a write through cache the same as FUA Date: Mon, 24 Jul 2023 16:55:06 -0600 Message-Id: <20230724225511.599870-4-axboe@kernel.dk> X-Mailer: git-send-email 2.40.1 In-Reply-To: <20230724225511.599870-1-axboe@kernel.dk> References: <20230724225511.599870-1-axboe@kernel.dk> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-xfs@vger.kernel.org Whether we have a write back cache and are using FUA or don't have a write back cache at all is the same situation. Treat them the same. This makes the IOMAP_DIO_WRITE_FUA name a bit misleading, as we have two cases that provide stable writes: 1) Volatile write cache with FUA writes 2) Normal write without a volatile write cache Rename that flag to IOMAP_DIO_STABLE_WRITE to make that clearer, and update some of the FUA comments as well. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/iomap/direct-io.c | 34 ++++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 7d627d43d10b..6b690fc22365 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -20,7 +20,7 @@ * Private flags for iomap_dio, must not overlap with the public ones in * iomap.h: */ -#define IOMAP_DIO_WRITE_FUA (1U << 28) +#define IOMAP_DIO_WRITE_THROUGH (1U << 28) #define IOMAP_DIO_NEED_SYNC (1U << 29) #define IOMAP_DIO_WRITE (1U << 30) #define IOMAP_DIO_DIRTY (1U << 31) @@ -219,7 +219,7 @@ static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, /* * Figure out the bio's operation flags from the dio request, the * mapping, and whether or not we want FUA. Note that we can end up - * clearing the WRITE_FUA flag in the dio request. + * clearing the WRITE_THROUGH flag in the dio request. */ static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio, const struct iomap *iomap, bool use_fua) @@ -233,7 +233,7 @@ static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio, if (use_fua) opflags |= REQ_FUA; else - dio->flags &= ~IOMAP_DIO_WRITE_FUA; + dio->flags &= ~IOMAP_DIO_WRITE_THROUGH; return opflags; } @@ -273,11 +273,13 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, * Use a FUA write if we need datasync semantics, this is a pure * data IO that doesn't require any metadata updates (including * after IO completion such as unwritten extent conversion) and - * the underlying device supports FUA. This allows us to avoid - * cache flushes on IO completion. + * the underlying device either supports FUA or doesn't have + * a volatile write cache. This allows us to avoid cache flushes + * on IO completion. */ if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) && - (dio->flags & IOMAP_DIO_WRITE_FUA) && bdev_fua(iomap->bdev)) + (dio->flags & IOMAP_DIO_WRITE_THROUGH) && + (bdev_fua(iomap->bdev) || !bdev_write_cache(iomap->bdev))) use_fua = true; } @@ -553,13 +555,16 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio->flags |= IOMAP_DIO_NEED_SYNC; /* - * For datasync only writes, we optimistically try - * using FUA for this IO. Any non-FUA write that - * occurs will clear this flag, hence we know before - * completion whether a cache flush is necessary. + * For datasync only writes, we optimistically try using + * WRITE_THROUGH for this IO. This flag requires either + * FUA writes through the device's write cache, or a + * normal write to a device without a volatile write + * cache. For the former, Any non-FUA write that occurs + * will clear this flag, hence we know before completion + * whether a cache flush is necessary. */ if (!(iocb->ki_flags & IOCB_SYNC)) - dio->flags |= IOMAP_DIO_WRITE_FUA; + dio->flags |= IOMAP_DIO_WRITE_THROUGH; } /* @@ -621,10 +626,11 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, iomap_dio_set_error(dio, ret); /* - * If all the writes we issued were FUA, we don't need to flush the - * cache on IO completion. Clear the sync flag for this case. + * If all the writes we issued were already written through to the + * media, we don't need to flush the cache on IO completion. Clear the + * sync flag for this case. */ - if (dio->flags & IOMAP_DIO_WRITE_FUA) + if (dio->flags & IOMAP_DIO_WRITE_THROUGH) dio->flags &= ~IOMAP_DIO_NEED_SYNC; WRITE_ONCE(iocb->private, dio->submit.poll_bio); From patchwork Mon Jul 24 22:55:07 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13325424 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id BA70CC04FDF for ; Mon, 24 Jul 2023 22:55:23 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230248AbjGXWzW (ORCPT ); Mon, 24 Jul 2023 18:55:22 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33464 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230073AbjGXWzV (ORCPT ); Mon, 24 Jul 2023 18:55:21 -0400 Received: from mail-pl1-x632.google.com (mail-pl1-x632.google.com [IPv6:2607:f8b0:4864:20::632]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 31C14E49 for ; Mon, 24 Jul 2023 15:55:20 -0700 (PDT) Received: by mail-pl1-x632.google.com with SMTP id d9443c01a7336-1bb85ed352bso3398565ad.0 for ; Mon, 24 Jul 2023 15:55:20 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20221208.gappssmtp.com; s=20221208; t=1690239319; x=1690844119; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=VaOldHsyTD5Hhzj5cIOnYQsnyuSsb37LHUEv6JZdWBU=; b=kWU+884CPmoOgYk3dplzwKBrvgeyCkYZpstecaAjynjjFeu99X4hes3fF3hrHaJ2FX rGITHDyrqLXX0tMIzib5aIHgvAftr79kYXMz6h7P3Lk6qts4qADy/KbcfHF6p3c7rn6n xV3k4ifjXdCkn9BoL4rdktFdkxY0NZ+YZ8SXtIK6y+IjY7O7+0orxvTQUdfZ1oY4jmqp fynnLQUHFMqv29FKcalYuBpmeRJNIVqB85yJTdTNGIYAt0M6nZwmJGKJw2Mo0i6c9Jw0 giYGzlY5BORCLwoFsEkPsFfe+CnuhrEGttyKbPBmJlogLGS74OiiaZGOCHbn76uk5hv7 CBmQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1690239319; x=1690844119; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=VaOldHsyTD5Hhzj5cIOnYQsnyuSsb37LHUEv6JZdWBU=; b=GePFTcN7Yijl9qf+656GFlteBEPNabeK72KOR/EUMQny5w9UnpCLsi8x8aW9ZTbI9P M6yre8p6VFX+awVZT6qk6QTbw5ADRhSUD/cit4rtEsN2oozuF7bXeNFaVxJUzRDSQ9A9 C+gGtMcFcLM6MlA5avvJjKa6XdUWJJLrMzK/FFb1Iyuxzhq+WrsImuWQPVvzq7FFxcnN 4DZRb0dSz4jSlP0NX8WCPUOzAxyC8/ONKMMkh/h/XXlr0crS2g9Ksbna1H5WAL3VlPUa V2ArAsiunKRxDL2egIQ3hYZreOQHbuyhneSemHq8LR6TK2RjUV/fuByQvRlZ1kY+AZaS 5qiQ== X-Gm-Message-State: ABy/qLb0RPJRdJBQHb0zbxzjA/uY7VR9GdkK6iFyE2O/eXiuJOF1lPlI 3aC4lVpyYwj/gzcSX/CHLI8Ljw== X-Google-Smtp-Source: APBJJlFGDAl/BePiqiyq9kDB9ah5cnhnCYsm7+4fdelWpYWIzFjJjVVKnmUzN9oI637OpbfH7TDZyw== X-Received: by 2002:a17:903:32c9:b0:1b8:5827:8763 with SMTP id i9-20020a17090332c900b001b858278763mr14369452plr.4.1690239319665; Mon, 24 Jul 2023 15:55:19 -0700 (PDT) Received: from localhost.localdomain ([198.8.77.157]) by smtp.gmail.com with ESMTPSA id p7-20020a1709026b8700b001acae9734c0sm9424733plk.266.2023.07.24.15.55.18 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 24 Jul 2023 15:55:19 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org, linux-xfs@vger.kernel.org Cc: hch@lst.de, andres@anarazel.de, david@fromorbit.com, djwong@kernel.org, Jens Axboe Subject: [PATCH 4/8] iomap: only set iocb->private for polled bio Date: Mon, 24 Jul 2023 16:55:07 -0600 Message-Id: <20230724225511.599870-5-axboe@kernel.dk> X-Mailer: git-send-email 2.40.1 In-Reply-To: <20230724225511.599870-1-axboe@kernel.dk> References: <20230724225511.599870-1-axboe@kernel.dk> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-xfs@vger.kernel.org iocb->private is only used for polled IO, where the completer will find the bio to poll through that field. Assign it when we're submitting a polled bio, and get rid of the dio->poll_bio indirection. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/iomap/direct-io.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 6b690fc22365..e4b9d9123b75 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -41,7 +41,6 @@ struct iomap_dio { struct { struct iov_iter *iter; struct task_struct *waiter; - struct bio *poll_bio; } submit; /* used for aio completion: */ @@ -63,12 +62,14 @@ static struct bio *iomap_dio_alloc_bio(const struct iomap_iter *iter, static void iomap_dio_submit_bio(const struct iomap_iter *iter, struct iomap_dio *dio, struct bio *bio, loff_t pos) { + struct kiocb *iocb = dio->iocb; + atomic_inc(&dio->ref); /* Sync dio can't be polled reliably */ - if ((dio->iocb->ki_flags & IOCB_HIPRI) && !is_sync_kiocb(dio->iocb)) { - bio_set_polled(bio, dio->iocb); - dio->submit.poll_bio = bio; + if ((iocb->ki_flags & IOCB_HIPRI) && !is_sync_kiocb(iocb)) { + bio_set_polled(bio, iocb); + WRITE_ONCE(iocb->private, bio); } if (dio->dops && dio->dops->submit_io) @@ -184,7 +185,6 @@ void iomap_dio_bio_end_io(struct bio *bio) * more IO to be issued to finalise filesystem metadata changes or * guarantee data integrity. */ - WRITE_ONCE(iocb->private, NULL); INIT_WORK(&dio->aio.work, iomap_dio_complete_work); queue_work(file_inode(iocb->ki_filp)->i_sb->s_dio_done_wq, &dio->aio.work); @@ -523,7 +523,6 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio->submit.iter = iter; dio->submit.waiter = current; - dio->submit.poll_bio = NULL; if (iocb->ki_flags & IOCB_NOWAIT) iomi.flags |= IOMAP_NOWAIT; @@ -633,8 +632,6 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (dio->flags & IOMAP_DIO_WRITE_THROUGH) dio->flags &= ~IOMAP_DIO_NEED_SYNC; - WRITE_ONCE(iocb->private, dio->submit.poll_bio); - /* * We are about to drop our additional submission reference, which * might be the last reference to the dio. There are three different From patchwork Mon Jul 24 22:55:08 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13325426 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id BC578C04FE1 for ; Mon, 24 Jul 2023 22:55:24 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230160AbjGXWzX (ORCPT ); Mon, 24 Jul 2023 18:55:23 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33488 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230186AbjGXWzW (ORCPT ); Mon, 24 Jul 2023 18:55:22 -0400 Received: from mail-pl1-x62d.google.com (mail-pl1-x62d.google.com [IPv6:2607:f8b0:4864:20::62d]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 213FE10E6 for ; Mon, 24 Jul 2023 15:55:21 -0700 (PDT) Received: by mail-pl1-x62d.google.com with SMTP id d9443c01a7336-1bba9539a23so1825925ad.1 for ; Mon, 24 Jul 2023 15:55:21 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20221208.gappssmtp.com; s=20221208; t=1690239320; x=1690844120; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=UkiYXAkH9GVD15ideYRW3eg5TFVpCBJh44wXJ9Qv8IA=; b=uMRNz4lYhIHghddKBkDuUHf0sS4xU5ctdO8KePyUfVQHcgs3wI++XVI2MyZ3fcz0ok GO8j6DrkoPJy8E0LBMD7NWiH5Be6+/grUqqthwMNBx1iyWW1q8g4L0oNULyvp8E20asX fnjUCaUqLN+ivFtIinQDYENNz/pQdPdufuuL3FOBlCJ65cWpI/QGU6W1Hq5ZJhBWBUk+ zapQYXyROrczWGS/MU/lvkk6Zdz2i5SjWZkMiR/WTQsI9izC2DULRCFQDweG4xDZEJVX 1ePCWR59SPbppPg9TK3asjiY1soPE7RXVMjq17RyT1H5R5LMNcOND1gb6potLHvmTkll 5NuQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1690239320; x=1690844120; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=UkiYXAkH9GVD15ideYRW3eg5TFVpCBJh44wXJ9Qv8IA=; b=OWKufJ7dUcEBmWeelIM1uzsHtJAa8bQjVz/bXVydues+DdVxcNrLznDKBtH0L4CNUb n+aCPEf7BOLEdi0jiQZphJTn8uOiI1vnR2FdKmvf7feLaxQ1I9XwUFZVOmMJQkGGTaDz f1sMJ6Dj6SNL6MzA2PaSfGYrk99EYeD0Gy9Rriwy+QgIgSq0qZAevINtM2vcDw6M9Csx CsR+sU1HIAA0j+jRzir3lejdVTAs+p1esfb6Fkdub0tWxqLzLnsp/xzgt1+Mtb8GLeD0 V/lyh/k6BRk+sAKWsR7xxhG9EHAAd5H2pwMvJnEO72OIAz58kSIAVpIbJlVJnlKcC43q mBaw== X-Gm-Message-State: ABy/qLa8jCOriTkefdab4dm/Nz0KyRc7PGuYMlZoVMo0GFtvdd35FK8j nPNyM6GDNiE0ymp4YsVWh5pjwQ== X-Google-Smtp-Source: APBJJlE75QLPlazs431saOk4q704bVzGQ9hXd/HdIVqUe6ICO+GIg7JpBbH53tBMy7aw60lbIeereg== X-Received: by 2002:a17:903:2305:b0:1b8:b0c4:2e3d with SMTP id d5-20020a170903230500b001b8b0c42e3dmr14474787plh.4.1690239320604; Mon, 24 Jul 2023 15:55:20 -0700 (PDT) Received: from localhost.localdomain ([198.8.77.157]) by smtp.gmail.com with ESMTPSA id p7-20020a1709026b8700b001acae9734c0sm9424733plk.266.2023.07.24.15.55.19 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 24 Jul 2023 15:55:20 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org, linux-xfs@vger.kernel.org Cc: hch@lst.de, andres@anarazel.de, david@fromorbit.com, djwong@kernel.org, Jens Axboe Subject: [PATCH 5/8] iomap: add IOMAP_DIO_INLINE_COMP Date: Mon, 24 Jul 2023 16:55:08 -0600 Message-Id: <20230724225511.599870-6-axboe@kernel.dk> X-Mailer: git-send-email 2.40.1 In-Reply-To: <20230724225511.599870-1-axboe@kernel.dk> References: <20230724225511.599870-1-axboe@kernel.dk> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-xfs@vger.kernel.org Rather than gate whether or not we need to punt a dio completion to a workqueue on whether the IO is a write or not, add an explicit flag for it. For now we treat them the same, reads always set the flags and async writes do not. No functional changes in this patch. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/iomap/direct-io.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index e4b9d9123b75..b943bc5c7b18 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -20,6 +20,7 @@ * Private flags for iomap_dio, must not overlap with the public ones in * iomap.h: */ +#define IOMAP_DIO_INLINE_COMP (1U << 27) #define IOMAP_DIO_WRITE_THROUGH (1U << 28) #define IOMAP_DIO_NEED_SYNC (1U << 29) #define IOMAP_DIO_WRITE (1U << 30) @@ -172,8 +173,10 @@ void iomap_dio_bio_end_io(struct bio *bio) goto release_bio; } - /* Read completion can always complete inline. */ - if (!(dio->flags & IOMAP_DIO_WRITE)) { + /* + * Flagged with IOMAP_DIO_INLINE_COMP, we can complete it inline + */ + if (dio->flags & IOMAP_DIO_INLINE_COMP) { WRITE_ONCE(iocb->private, NULL); iomap_dio_complete_work(&dio->aio.work); goto release_bio; @@ -528,6 +531,9 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, iomi.flags |= IOMAP_NOWAIT; if (iov_iter_rw(iter) == READ) { + /* reads can always complete inline */ + dio->flags |= IOMAP_DIO_INLINE_COMP; + if (iomi.pos >= dio->i_size) goto out_free_dio; From patchwork Mon Jul 24 22:55:09 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13325425 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8B1F6C001E0 for ; Mon, 24 Jul 2023 22:55:25 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230207AbjGXWzY (ORCPT ); Mon, 24 Jul 2023 18:55:24 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33504 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230073AbjGXWzX (ORCPT ); Mon, 24 Jul 2023 18:55:23 -0400 Received: from mail-pl1-x634.google.com (mail-pl1-x634.google.com [IPv6:2607:f8b0:4864:20::634]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 28ED3E49 for ; Mon, 24 Jul 2023 15:55:22 -0700 (PDT) Received: by mail-pl1-x634.google.com with SMTP id d9443c01a7336-1bbadf9ed37so1478795ad.0 for ; Mon, 24 Jul 2023 15:55:22 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20221208.gappssmtp.com; s=20221208; t=1690239321; x=1690844121; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=4m73hDbmfHkB6vBAc3X7AmWd4GXS2D47NYfUBsYjTeE=; b=VG7ninWMl0JZlPdtIdNJcgkEXQh8MU+lBObbQkV5neVUmOxeTsurIAurlrNjadlfEk DbgsRETI6qP4mK3+D6R6o7o+SsqRLBHSuqTmTKPD18i6b/MNyPETV3U+eenLXgF7ot9d bviEE8LIdTNW+55BzbCtmr4SdSJmLpeCtdWBuA7RKR+K6glPgb7W5iE1csdiKxcQVqON O1Aelyg5+JUb5Yz3qcWbAqMoHKehauwOhIamUhoUOFI09lapOejJkVANZvSOrL60CYlj mOs713G+KiVtz022nbct3jHESv7OWvwynKBqfPuzycunxnsQdS2mFLpirHxtZKCx+SNn dVqA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1690239321; x=1690844121; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=4m73hDbmfHkB6vBAc3X7AmWd4GXS2D47NYfUBsYjTeE=; b=I7XNqnraYdlUqP2N080ggz1dOLkJr1D9hylrUKBgqgB2trAx+6t2HEYOEP9B75/oSJ lzqxlYjKH9fXYAKkNIHVeCQRG7E96pKB58B6UCrVVpn5Qo1E2QRJYtFgbVElDT9Yyddx 0EgjUNYAXTs/Wiuk22po8WLaix2A9/kRHvXX4hvAu+0owdLYXq75JX520PGmWbYsc81+ IQhVZwSCPr3aCF5q6CRA513BMqmlC0TBfHQvfais/SvGoHvhZ+meR3WwajngweCw6GRP crELCHZJxYycoddsy4bYayxM3InVtG+wLram1batC6XEghGuRj4qwSaHoLGOXWdPz/Za EBxQ== X-Gm-Message-State: ABy/qLaeechGR5OVRvUzR/5y/sb1sEtZONY+bi/RvYGmURv47ooEU+6i PxSu4mjxfPv9fThO8HO7VltJqh/xZppSeFKiisk= X-Google-Smtp-Source: APBJJlGVStg2IqBph0zTI/BetjM8/WiT7C7LPmmDKrWD9iKfcw4MKCaPlznHf9Vaj0ssvFl3I+fUsg== X-Received: by 2002:a17:902:d4c6:b0:1b8:85c4:48f5 with SMTP id o6-20020a170902d4c600b001b885c448f5mr15164004plg.2.1690239321659; Mon, 24 Jul 2023 15:55:21 -0700 (PDT) Received: from localhost.localdomain ([198.8.77.157]) by smtp.gmail.com with ESMTPSA id p7-20020a1709026b8700b001acae9734c0sm9424733plk.266.2023.07.24.15.55.20 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 24 Jul 2023 15:55:21 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org, linux-xfs@vger.kernel.org Cc: hch@lst.de, andres@anarazel.de, david@fromorbit.com, djwong@kernel.org, Jens Axboe Subject: [PATCH 6/8] fs: add IOCB flags related to passing back dio completions Date: Mon, 24 Jul 2023 16:55:09 -0600 Message-Id: <20230724225511.599870-7-axboe@kernel.dk> X-Mailer: git-send-email 2.40.1 In-Reply-To: <20230724225511.599870-1-axboe@kernel.dk> References: <20230724225511.599870-1-axboe@kernel.dk> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-xfs@vger.kernel.org Async dio completions generally happen from hard/soft IRQ context, which means that users like iomap may need to defer some of the completion handling to a workqueue. This is less efficient than having the original issuer handle it, like we do for sync IO, and it adds latency to the completions. Add IOCB_DIO_CALLER_COMP, which the issuer can set if it is able to safely punt these completions to a safe context. If the dio handler is aware of this flag, assign a callback handler in kiocb->dio_complete and associated data io kiocb->private. The issuer will then call this handler with that data from task context. No functional changes in this patch. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 35 +++++++++++++++++++++++++++++++++-- 1 file changed, 33 insertions(+), 2 deletions(-) diff --git a/include/linux/fs.h b/include/linux/fs.h index 6867512907d6..1e6dbe309d52 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -338,6 +338,20 @@ enum rw_hint { #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) +/* + * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the + * iocb completion can be passed back to the owner for execution from a safe + * context rather than needing to be punted through a workqueue. If this + * flag is set, the bio completion handling may set iocb->dio_complete to a + * handler function and iocb->private to context information for that handler. + * The issuer should call the handler with that context information from task + * context to complete the processing of the iocb. Note that while this + * provides a task context for the dio_complete() callback, it should only be + * used on the completion side for non-IO generating completions. It's fine to + * call blocking functions from this callback, but they should not wait for + * unrelated IO (like cache flushing, new IO generation, etc). + */ +#define IOCB_DIO_CALLER_COMP (1 << 22) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ @@ -351,7 +365,8 @@ enum rw_hint { { IOCB_WRITE, "WRITE" }, \ { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ - { IOCB_ALLOC_CACHE, "ALLOC_CACHE" } + { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ + { IOCB_DIO_CALLER_COMP, "CALLER_COMP" } struct kiocb { struct file *ki_filp; @@ -360,7 +375,23 @@ struct kiocb { void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ - struct wait_page_queue *ki_waitq; /* for async buffered IO */ + union { + /* + * Only used for async buffered reads, where it denotes the + * page waitqueue associated with completing the read. Valid + * IFF IOCB_WAITQ is set. + */ + struct wait_page_queue *ki_waitq; + /* + * Can be used for O_DIRECT IO, where the completion handling + * is punted back to the issuer of the IO. May only be set + * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer + * must then check for presence of this handler when ki_complete + * is invoked. The data passed in to this handler must be + * assigned to ->private when dio_complete is assigned. + */ + ssize_t (*dio_complete)(void *data); + }; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) From patchwork Mon Jul 24 22:55:10 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13325427 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 1CDC1C001B0 for ; Mon, 24 Jul 2023 22:55:26 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230073AbjGXWzZ (ORCPT ); Mon, 24 Jul 2023 18:55:25 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33532 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230186AbjGXWzX (ORCPT ); Mon, 24 Jul 2023 18:55:23 -0400 Received: from mail-pl1-x636.google.com (mail-pl1-x636.google.com [IPv6:2607:f8b0:4864:20::636]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 173A810E3 for ; Mon, 24 Jul 2023 15:55:23 -0700 (PDT) Received: by mail-pl1-x636.google.com with SMTP id d9443c01a7336-1bbadf9ed37so1478855ad.0 for ; Mon, 24 Jul 2023 15:55:23 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20221208.gappssmtp.com; s=20221208; t=1690239322; x=1690844122; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=pjL6qHDAMp43y83zcgUBo4WIWL310kwBcjaLigNwC5o=; b=RZaFqrVRlaMJTDgYZnV9ei7uQv6WyNsF/3oHK39dfgfrQoSoiKZx5Eu+nfPbPxcnju L3aVKbpb1Y5giwjoeiuVFNhnQLpERXvLpjLO1BhHxqW/Fuj/ACjJfp03hGxwK03xwng9 WtxNwN9MAuHT8Xs7Foteb3OuO35pLd8D5rAbvOizr7LQg1uaBmTAmGDklYfWDvofnpj/ bTyhlSDrLjTDzfZXQU9RRR2RAYarRUxb2yFbuwUz4izvkyIdwKLTZ3HLT+bcAUPfY3va sJJ8oopd5mxkNnfQ8xT6GxZPRTwsOlRa44PI7r14X6sIMRlG/wbdqDbDub+Ea6x/mnh/ XJlg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1690239322; x=1690844122; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=pjL6qHDAMp43y83zcgUBo4WIWL310kwBcjaLigNwC5o=; b=PSov7Bv6YQKa31qd3REqdLH79AVcOXx93Af+i2bajezRe569097VLDdKK/BtVGBWrk R+OXO9xE3pkYk00wFFQTMhwpyurxsC6IYRP+su5eXXLAeE7q1DRZ4s/ZvDik9OBcNifM duzq4isFi8r8D7xabbxfuimcH0xabRk9tRdAe7722W5+tMgwPyd07P9fGLVus2Vokp5q 0/4Ck8q1o5mlr/oO9tRhvkgyfGBDmhU9p0axugIfVOjfhfws97pZZXSE2K6WUH0fHCQl 3hzHrfbBKmo8yB2mNxYeJyqW3hGzbNOUs98NYSR9YwtARVAQA0v32DxBMq6FRIL8XEVR OaLQ== X-Gm-Message-State: ABy/qLYx6YQ11hMtuT9yIzX1JNVPNHvx1RsvXyRVJWMNhr+mOsELilpb Q0l34MQQuO/RtZH68vDKWqIsdw== X-Google-Smtp-Source: APBJJlGqVaFhkrrW+NY3IBwC4JQe4MjPRh7n5pVFU87+M8pw/bZU9P+wACt1FrfPaWZfwkFAMEgi+A== X-Received: by 2002:a17:902:d4c6:b0:1b8:85c4:48f5 with SMTP id o6-20020a170902d4c600b001b885c448f5mr15164040plg.2.1690239322608; Mon, 24 Jul 2023 15:55:22 -0700 (PDT) Received: from localhost.localdomain ([198.8.77.157]) by smtp.gmail.com with ESMTPSA id p7-20020a1709026b8700b001acae9734c0sm9424733plk.266.2023.07.24.15.55.21 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 24 Jul 2023 15:55:22 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org, linux-xfs@vger.kernel.org Cc: hch@lst.de, andres@anarazel.de, david@fromorbit.com, djwong@kernel.org, Jens Axboe Subject: [PATCH 7/8] io_uring/rw: add write support for IOCB_DIO_CALLER_COMP Date: Mon, 24 Jul 2023 16:55:10 -0600 Message-Id: <20230724225511.599870-8-axboe@kernel.dk> X-Mailer: git-send-email 2.40.1 In-Reply-To: <20230724225511.599870-1-axboe@kernel.dk> References: <20230724225511.599870-1-axboe@kernel.dk> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-xfs@vger.kernel.org If the filesystem dio handler understands IOCB_DIO_CALLER_COMP, we'll get a kiocb->ki_complete() callback with kiocb->dio_complete set. In that case, rather than complete the IO directly through task_work, queue up an intermediate task_work handler that first processes this callback and then immediately completes the request. For XFS, this avoids a punt through a workqueue, which is a lot less efficient and adds latency to lower queue depth (or sync) O_DIRECT writes. Only do this for non-polled IO, as polled IO doesn't need this kind of deferral as it always completes within the task itself. This then avoids a check for deferral in the polled IO completion handler. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- io_uring/rw.c | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) diff --git a/io_uring/rw.c b/io_uring/rw.c index 1bce2208b65c..f19f65b3f0ee 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -105,6 +105,7 @@ int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) } else { rw->kiocb.ki_ioprio = get_current_ioprio(); } + rw->kiocb.dio_complete = NULL; rw->addr = READ_ONCE(sqe->addr); rw->len = READ_ONCE(sqe->len); @@ -285,6 +286,14 @@ static inline int io_fixup_rw_res(struct io_kiocb *req, long res) void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts) { + struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); + + if (rw->kiocb.dio_complete) { + long res = rw->kiocb.dio_complete(rw->kiocb.private); + + io_req_set_res(req, io_fixup_rw_res(req, res), 0); + } + io_req_io_end(req); if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) { @@ -300,9 +309,11 @@ static void io_complete_rw(struct kiocb *kiocb, long res) struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb); struct io_kiocb *req = cmd_to_io_kiocb(rw); - if (__io_complete_rw_common(req, res)) - return; - io_req_set_res(req, io_fixup_rw_res(req, res), 0); + if (!rw->kiocb.dio_complete) { + if (__io_complete_rw_common(req, res)) + return; + io_req_set_res(req, io_fixup_rw_res(req, res), 0); + } req->io_task_work.func = io_req_rw_complete; __io_req_task_work_add(req, IOU_F_TWQ_LAZY_WAKE); } @@ -916,6 +927,15 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) } kiocb->ki_flags |= IOCB_WRITE; + /* + * For non-polled IO, set IOCB_DIO_CALLER_COMP, stating that our handler + * groks deferring the completion to task context. This isn't + * necessary and useful for polled IO as that can always complete + * directly. + */ + if (!(kiocb->ki_flags & IOCB_HIPRI)) + kiocb->ki_flags |= IOCB_DIO_CALLER_COMP; + if (likely(req->file->f_op->write_iter)) ret2 = call_write_iter(req->file, kiocb, &s->iter); else if (req->file->f_op->write) From patchwork Mon Jul 24 22:55:11 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13325428 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 792F1C001DE for ; Mon, 24 Jul 2023 22:55:27 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230186AbjGXWz0 (ORCPT ); Mon, 24 Jul 2023 18:55:26 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33562 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230301AbjGXWzZ (ORCPT ); Mon, 24 Jul 2023 18:55:25 -0400 Received: from mail-pl1-x62f.google.com (mail-pl1-x62f.google.com [IPv6:2607:f8b0:4864:20::62f]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 1141D100 for ; Mon, 24 Jul 2023 15:55:24 -0700 (PDT) Received: by mail-pl1-x62f.google.com with SMTP id d9443c01a7336-1bba9539a23so1826095ad.1 for ; Mon, 24 Jul 2023 15:55:24 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20221208.gappssmtp.com; s=20221208; t=1690239323; x=1690844123; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=+DqlprFT3rIJ93hb4ytZ/U+5DLbYbXZZtopIzdBjbSs=; b=qZyXJ5GOrSNROW0VLYT+HLv0T1KL6Mh1WHD9ZALp0ngmW4xvke7aJv0gGltZeOBrt7 bYoLfr0qjEzJN0R3KP25nnJ08in3S5axLYskHHTWQa8/hIZk22fjqiljQemLyYOewTUp vM3o42lLuoR0DnSDGIF9IyswN6hE/xUDaE7CqjnM3Cpjv/PnCLuQplD8m28cfjs+DjJL 86VtF80yyUGCWXrYz3lDs1YP135U8OlFUr8wntQYEUacAU8U5UdksHX+IxUYL7C77Wqn Egf3Snu+mupFd09XqzSbFVwpjOB5GTaRwQ1+lHrY5pxcqXhGEa7adagVSIppXj3681SW PZLQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1690239323; x=1690844123; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=+DqlprFT3rIJ93hb4ytZ/U+5DLbYbXZZtopIzdBjbSs=; b=M5b2fytB+UGU0p3WJB7qhO02+IPacJSXy0076dtSLxsYhdvLyEMlL3KzlXl1weHtSW piaZCh+yCxq8jU4f8hEUYhdQxcGQtShRC8XyrP2QULGqnIUf930Y8ViiNrklqV13ab+4 fh/vI0bAyxLwS+9as4/mMWeNoH423/aAnSmQYtCzj4YQ7YUgzZ/HxPHZAei61Vgw3xyb qwPNDxxuxRxxpzESXvoUTEwEfnLymPar1C82I9MMD1CR6eKMVymIxfB1GyyEVLJZpDEW fYfzYy6Xff6M3+HgcOMc8Ot1jzs69vizMMs8uO6D58dvq81Jc3Xls4c0MJ/BdCub+UT/ vB8w== X-Gm-Message-State: ABy/qLazbq04BGlEp3ma0AZJNkiJUiqlibtOqTdrdN3H2t16DT1YJDHw j5iVTzSOReOlw0OaEP+nX5PYFw== X-Google-Smtp-Source: APBJJlF7N9AmmkBTysR/mafF4wuzyAwYLu/QLUnYzQrf7ApEXKA6OZJFE1/IL+aC4TOHfQMOGzedBg== X-Received: by 2002:a17:902:ea01:b0:1bb:83ec:832 with SMTP id s1-20020a170902ea0100b001bb83ec0832mr10583875plg.2.1690239323510; Mon, 24 Jul 2023 15:55:23 -0700 (PDT) Received: from localhost.localdomain ([198.8.77.157]) by smtp.gmail.com with ESMTPSA id p7-20020a1709026b8700b001acae9734c0sm9424733plk.266.2023.07.24.15.55.22 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 24 Jul 2023 15:55:23 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org, linux-xfs@vger.kernel.org Cc: hch@lst.de, andres@anarazel.de, david@fromorbit.com, djwong@kernel.org, Jens Axboe Subject: [PATCH 8/8] iomap: support IOCB_DIO_CALLER_COMP Date: Mon, 24 Jul 2023 16:55:11 -0600 Message-Id: <20230724225511.599870-9-axboe@kernel.dk> X-Mailer: git-send-email 2.40.1 In-Reply-To: <20230724225511.599870-1-axboe@kernel.dk> References: <20230724225511.599870-1-axboe@kernel.dk> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-xfs@vger.kernel.org If IOCB_DIO_CALLER_COMP is set, utilize that to set kiocb->dio_complete handler and data for that callback. Rather than punt the completion to a workqueue, we pass back the handler and data to the issuer and will get a callback from a safe task context. Using the following fio job to randomly dio write 4k blocks at queue depths of 1..16: fio --name=dio-write --filename=/data1/file --time_based=1 \ --runtime=10 --bs=4096 --rw=randwrite --norandommap --buffered=0 \ --cpus_allowed=4 --ioengine=io_uring --iodepth=$depth shows the following results before and after this patch: Stock Patched Diff ======================================= QD1 155K 162K + 4.5% QD2 290K 313K + 7.9% QD4 533K 597K +12.0% QD8 604K 827K +36.9% QD16 615K 845K +37.4% which shows nice wins all around. If we factored in per-IOP efficiency, the wins look even nicer. This becomes apparent as queue depth rises, as the offloaded workqueue completions runs out of steam. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/iomap/direct-io.c | 62 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 60 insertions(+), 2 deletions(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index b943bc5c7b18..bcd3f8cf5ea4 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -20,6 +20,7 @@ * Private flags for iomap_dio, must not overlap with the public ones in * iomap.h: */ +#define IOMAP_DIO_CALLER_COMP (1U << 26) #define IOMAP_DIO_INLINE_COMP (1U << 27) #define IOMAP_DIO_WRITE_THROUGH (1U << 28) #define IOMAP_DIO_NEED_SYNC (1U << 29) @@ -132,6 +133,11 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio) } EXPORT_SYMBOL_GPL(iomap_dio_complete); +static ssize_t iomap_dio_deferred_complete(void *data) +{ + return iomap_dio_complete(data); +} + static void iomap_dio_complete_work(struct work_struct *work) { struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work); @@ -182,6 +188,31 @@ void iomap_dio_bio_end_io(struct bio *bio) goto release_bio; } + /* + * If this dio is flagged with IOMAP_DIO_CALLER_COMP, then schedule + * our completion that way to avoid an async punt to a workqueue. + */ + if (dio->flags & IOMAP_DIO_CALLER_COMP) { + /* only polled IO cares about private cleared */ + iocb->private = dio; + iocb->dio_complete = iomap_dio_deferred_complete; + + /* + * Invoke ->ki_complete() directly. We've assigned our + * dio_complete callback handler, and since the issuer set + * IOCB_DIO_CALLER_COMP, we know their ki_complete handler will + * notice ->dio_complete being set and will defer calling that + * handler until it can be done from a safe task context. + * + * Note that the 'res' being passed in here is not important + * for this case. The actual completion value of the request + * will be gotten from dio_complete when that is run by the + * issuer. + */ + iocb->ki_complete(iocb, 0); + goto release_bio; + } + /* * Async DIO completion that requires filesystem level completion work * gets punted to a work queue to complete as the operation may require @@ -278,12 +309,17 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, * after IO completion such as unwritten extent conversion) and * the underlying device either supports FUA or doesn't have * a volatile write cache. This allows us to avoid cache flushes - * on IO completion. + * on IO completion. If we can't use writethrough and need to + * sync, disable in-task completions as dio completion will + * need to call generic_write_sync() which will do a blocking + * fsync / cache flush call. */ if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) && (dio->flags & IOMAP_DIO_WRITE_THROUGH) && (bdev_fua(iomap->bdev) || !bdev_write_cache(iomap->bdev))) use_fua = true; + else if (dio->flags & IOMAP_DIO_NEED_SYNC) + dio->flags &= ~IOMAP_DIO_CALLER_COMP; } /* @@ -298,10 +334,23 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, goto out; /* - * We can only poll for single bio I/Os. + * We can only do deferred completion for pure overwrites that + * don't require additional IO at completion. This rules out + * writes that need zeroing or extent conversion, extend + * the file size, or issue journal IO or cache flushes + * during completion processing. */ if (need_zeroout || + ((dio->flags & IOMAP_DIO_NEED_SYNC) && !use_fua) || ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) + dio->flags &= ~IOMAP_DIO_CALLER_COMP; + + /* + * The rules for polled IO completions follow the guidelines as the + * ones we set for inline and deferred completions. If none of those + * are available for this IO, clear the polled flag. + */ + if (!(dio->flags & (IOMAP_DIO_INLINE_COMP|IOMAP_DIO_CALLER_COMP))) dio->iocb->ki_flags &= ~IOCB_HIPRI; if (need_zeroout) { @@ -547,6 +596,15 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, iomi.flags |= IOMAP_WRITE; dio->flags |= IOMAP_DIO_WRITE; + /* + * Flag as supporting deferred completions, if the issuer + * groks it. This can avoid a workqueue punt for writes. + * We may later clear this flag if we need to do other IO + * as part of this IO completion. + */ + if (iocb->ki_flags & IOCB_DIO_CALLER_COMP) + dio->flags |= IOMAP_DIO_CALLER_COMP; + if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) { ret = -EAGAIN; if (iomi.pos >= dio->i_size ||