From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-qt1-f173.google.com (mail-qt1-f173.google.com [209.85.160.173]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 1B8C737104C for ; Thu, 11 Jun 2026 08:35:31 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.160.173 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1781166934; cv=none; b=EXRYJUN/JencGNm8lnowOFZuVkmjjJGSxV9cSj9ss/uFnVMyokKrXg/g/xrjmJqlyOaGiUEtIT0zuVu0/S+86n1Iok5A+8XDkPNdzSXZJUf8TrWcfbkXvmpO6GD6H3qHqro2MDmVP2sgvt4kUgLQzxM7wXeiu3aqshykMztNG24= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1781166934; c=relaxed/simple; bh=adrzxXaPLJGP7roNgSQZ5MepEJ3NFhQuSaSwV81bBII=; h=From:To:Cc:Subject:Date:Message-ID:MIME-Version; b=SRdaHryQF4RExWlwo/dKmmmG4+js8GojvBEVo9bwrWSWBMaZZUmkLQ5zh500M2fR1Jju2mhv3Jb2Ryfmv8NevPs5iAMDQlBLrsDQVxp6YJDB39feYOddog4RwFPKqJiUfY+sgkYwF733zKpfl8D9OLJCXjbvI2OxqEfIsC2mqI4= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=OJaQgBI/; arc=none smtp.client-ip=209.85.160.173 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="OJaQgBI/" Received: by mail-qt1-f173.google.com with SMTP id d75a77b69052e-5176d4c14f5so62161401cf.0 for ; Thu, 11 Jun 2026 01:35:31 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1781166931; x=1781771731; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:from:to:cc:subject:date:message-id:reply-to; bh=IWa6r+6TmQG8v9LMqLWqXodbxfzDu8ypmi09vJ5cWrI=; b=OJaQgBI/b9K/6iVRWDI85qD8VbWUkX/uX4Nj/LWhx/C2J2IsHpPVi+vYTFw5SrwG2j vNqmvwggnlgLZo9qKiRkbtHnPvZC4PbhUqn0YePb06eVOLdIntDzhgb1/Ann4N5V2dFa NM8L9W56ly3zeqjY9Focu8bF7mhFtsZwNaJbUflf/cU4XVJ3T6FwspBC0/t1IDwg61Ua gF3Cl/j5w7IimXfxDO/ZzHri9tNGZilr90mOnxv15sHmzmj92V4DSRwbp6REuFJcmuhv 5OALz8Rd/JoETip4BkxLilLVUAeA9ObB+bgm1OOql7ZuaIX2oc0Mmh2AvS7iBAoToogq ouKA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1781166931; x=1781771731; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:x-gm-gg:x-gm-message-state:from:to:cc:subject:date :message-id:reply-to; bh=IWa6r+6TmQG8v9LMqLWqXodbxfzDu8ypmi09vJ5cWrI=; b=qMsG5G/+DZ9o/ffYji1jkwt1+vBZQNonFxgLJ+IoMSasoPgcGvWDgj9uMApG0HCuXz rb8+0JhLcFgXk1tpz1x/rz09DbYZ+KDO1vYgs/vgUvVWA2b41jzQdQ0T8507jmr0Vm1K 2r2Sc+9K0N80XmrBbulnILRm/2rfRVEaJH0DCQwtwcKXJOOVM1T1BBgNt4DD6B6Rd77p /yQuBLrjpBZCJeAJ3YY3PL+q8eV1c+9bdGDkhOb2kW7y2MfnttvUoEwe2ZqerJespL3+ doJ3oLicpBmrh4+J1V2kqq5aI2uKmCzh2JxWTYSP/WhnafA/HULzsrflEMNGXDbiDi1l g52Q== X-Forwarded-Encrypted: i=1; AFNElJ+uU00ecvjhfS10UWgBOnm5PPz324vwLAGCyvaWEYTfMhxVqPUp2LNEmaAUUmJDgjErL+cN6jBwuBisq7c=@vger.kernel.org X-Gm-Message-State: AOJu0YyZYE86ykJzFW6dMCpX3Zd/P/XJOc0x3Eai3oMUbyXTKHh32PC+ 0lkZP+WTMpqDNegI6LnsOmQHlclm2ZmblCW3OZGOmu0nhu6lvPNTtizM X-Gm-Gg: Acq92OGZLEd3QvbKJ1SytI4IBjCd0CsW0dCGRfmPlGI4bTAMKuq2MWVCwBEgZK1hpCD fcLoscTe+1LFi+FBG6lL2NX4ElUomLYUSDe49Vjb2hbXUa5B1W+fG/Ifm3QHDX47o6L46O74XqZ 73RMd6F6guo0JDm4f+cSbpXwqrwoDs5Q9r2jMvNkKiWww7KyHYT5PEllN91VrwljbgmLEMOV0s6 lCC5Fu+YBOaSiyslipzYjPS3ImqSIVs39l9EYfE8SrhaQllR+wzC0ofGrR9/Sbtah0382kfjNLm R1JFza/xPSW3kh2ijeK3elBCyQRNKmrb24S+5J0U/uwqLoXq2PzLKEtWMjmtDK5CuTKoj+FaI3g EunNa1Lb2EkHzJaUhs8d8bEOT0VB3RvVC2AB18EQyWbImI/b1XRJ+GrYmJQvRWjGQrCvPU6E1YZ bfLq/D+u4cqEe+YM7I452pj2h6Z3pXgM1jGuRhe7wdeW0mK9gtIuy8uQ== X-Received: by 2002:a05:622a:99a:b0:516:d4b1:48cd with SMTP id d75a77b69052e-517edd0ce26mr26786061cf.2.1781166930798; Thu, 11 Jun 2026 01:35:30 -0700 (PDT) Received: from yocto.rz.uni-frankfurt.de ([141.2.113.162]) by smtp.gmail.com with ESMTPSA id d75a77b69052e-517ef40db7bsm11797141cf.7.2026.06.11.01.35.28 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 11 Jun 2026 01:35:29 -0700 (PDT) From: Abd-Alrhman Masalkhi To: song@kernel.org, yukuai@fygo.io, magiclinan@didiglobal.com, xiao@kernel.org, vverma@digitalocean.com, axboe@kernel.dk Cc: linux-raid@vger.kernel.org, linux-kernel@vger.kernel.org, Abd-Alrhman Masalkhi Subject: [PATCH] md/raid1: honor REQ_NOWAIT when waiting for behind writes Date: Thu, 11 Jun 2026 08:35:14 +0000 Message-ID: <20260611083514.754922-1-abd.masalkhi@gmail.com> X-Mailer: git-send-email 2.43.0 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit raid1 supports REQ_NOWAIT reads by avoiding waits in the barrier path through wait_read_barrier(). However, a read can still block on a WriteMostly device when the array uses a bitmap and there are outstanding behind writes. In that case raid1 unconditionally calls wait_behind_writes(), which may sleep until all behind writes complete. As a result, a REQ_NOWAIT read can block despite the caller explicitly requesting non-blocking behavior. This ensures that raid1 consistently honors REQ_NOWAIT reads across all paths that may otherwise wait for behind writes. Fixes: 5aa705039c4f ("md: raid1 add nowait support") Signed-off-by: Abd-Alrhman Masalkhi --- drivers/md/md-bitmap.c | 9 +++++++-- drivers/md/md-bitmap.h | 2 +- drivers/md/md-llbitmap.c | 13 ++++++++----- drivers/md/md.c | 2 +- drivers/md/raid1.c | 10 +++++++--- 5 files changed, 24 insertions(+), 12 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 028b9ca8ce52..1206e31f323a 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2063,18 +2063,23 @@ static void bitmap_end_behind_write(struct mddev *mddev) bitmap->mddev->bitmap_info.max_write_behind); } -static void bitmap_wait_behind_writes(struct mddev *mddev) +static bool bitmap_wait_behind_writes(struct mddev *mddev, bool nowait) { struct bitmap *bitmap = mddev->bitmap; /* wait for behind writes to complete */ if (bitmap && atomic_read(&bitmap->behind_writes) > 0) { + if (nowait) + return false; + pr_debug("md:%s: behind writes in progress - waiting to stop.\n", mdname(mddev)); /* need to kick something here to make sure I/O goes? */ wait_event(bitmap->behind_wait, atomic_read(&bitmap->behind_writes) == 0); } + + return true; } static void bitmap_destroy(struct mddev *mddev) @@ -2084,7 +2089,7 @@ static void bitmap_destroy(struct mddev *mddev) if (!bitmap) /* there was no bitmap */ return; - bitmap_wait_behind_writes(mddev); + bitmap_wait_behind_writes(mddev, false); if (!test_bit(MD_SERIALIZE_POLICY, &mddev->flags)) mddev_destroy_serial_pool(mddev, NULL); diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 214f623c7e79..f46674bdfeb9 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -98,7 +98,7 @@ struct bitmap_operations { void (*start_behind_write)(struct mddev *mddev); void (*end_behind_write)(struct mddev *mddev); - void (*wait_behind_writes)(struct mddev *mddev); + bool (*wait_behind_writes)(struct mddev *mddev, bool nowait); md_bitmap_fn *start_write; md_bitmap_fn *end_write; diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c index 1adc5b117821..5a4e2abaa757 100644 --- a/drivers/md/md-llbitmap.c +++ b/drivers/md/md-llbitmap.c @@ -1574,16 +1574,19 @@ static void llbitmap_end_behind_write(struct mddev *mddev) wake_up(&llbitmap->behind_wait); } -static void llbitmap_wait_behind_writes(struct mddev *mddev) +static bool llbitmap_wait_behind_writes(struct mddev *mddev, bool nowait) { struct llbitmap *llbitmap = mddev->bitmap; - if (!llbitmap) - return; + if (llbitmap && atomic_read(&llbitmap->behind_writes) > 0) { + if (nowait) + return false; - wait_event(llbitmap->behind_wait, - atomic_read(&llbitmap->behind_writes) == 0); + wait_event(llbitmap->behind_wait, + atomic_read(&llbitmap->behind_writes) == 0); + } + return true; } static ssize_t bits_show(struct mddev *mddev, char *page) diff --git a/drivers/md/md.c b/drivers/md/md.c index 096bb64e87bd..d1465bcd86c8 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7050,7 +7050,7 @@ EXPORT_SYMBOL_GPL(md_stop_writes); static void mddev_detach(struct mddev *mddev) { if (md_bitmap_enabled(mddev, false)) - mddev->bitmap_ops->wait_behind_writes(mddev); + mddev->bitmap_ops->wait_behind_writes(mddev, false); if (mddev->pers && mddev->pers->quiesce && !is_md_suspended(mddev)) { mddev->pers->quiesce(mddev, 1); mddev->pers->quiesce(mddev, 0); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index b1ed4cc6ade4..b2d7c13b64bd 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1341,6 +1341,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, int max_sectors; int rdisk; bool r1bio_existed = !!r1_bio; + bool nowait = bio->bi_opf & REQ_NOWAIT; /* * An md cloned bio indicates we are in the error path. @@ -1360,8 +1361,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, * Still need barrier for READ in case that whole * array is frozen. */ - if (!wait_read_barrier(conf, bio->bi_iter.bi_sector, - bio->bi_opf & REQ_NOWAIT)) { + if (!wait_read_barrier(conf, bio->bi_iter.bi_sector, nowait)) { bio_wouldblock_error(bio); return; } @@ -1402,7 +1402,11 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, * over-take any writes that are 'behind' */ mddev_add_trace_msg(mddev, "raid1 wait behind writes"); - mddev->bitmap_ops->wait_behind_writes(mddev); + if (!mddev->bitmap_ops->wait_behind_writes(mddev, nowait)) { + bio_wouldblock_error(bio); + set_bit(R1BIO_Returned, &r1_bio->state); + goto err_handle; + } } if (max_sectors < bio_sectors(bio)) { -- 2.43.0