From nobody Sun Feb 8 12:58:14 2026 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; dkim=fail; spf=pass (zoho.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=gmail.com ARC-Seal: i=1; a=rsa-sha256; t=1564508700; cv=none; d=zoho.com; s=zohoarc; b=Wrbwkc2E52nUrwTwbBiZwr4QZycoF4EiR7eHUeuTVEzqtbAjegI9o4yW6/Tz0PQGfKDpCakOpnNqZ2TguJ3qZVgKK8UTu7bMUIfPpyATRX4aFeMNJVGBhmxz4CSPaHLzQ8C9GWLCuIJhTAPXCtON/veAwbLfEw0Bpurxk9YMCWg= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zoho.com; s=zohoarc; t=1564508700; h=Content-Transfer-Encoding:Cc:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To:ARC-Authentication-Results; bh=VIbCCiqkXwkRR3OlBzyvEa8q9jsIq4iRUCXYKqboH9I=; b=He2pmEU/8st+346ieWldCxGPlyY3KVwwGRWyoqOJApWCzEO56K3wDPhXmQmIjS8+V9o+TFI9DOsUPvz1I+MkGlfLMUsZ+JSJHMt3bJS9nGaF9bnyEt/EUO+v0bObQmUQ2EZDad1nz/ylEvfWLWG7QnjZLAqgpxT/iP5egaADFKE= ARC-Authentication-Results: i=1; mx.zoho.com; dkim=fail; spf=pass (zoho.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail header.from= (p=none dis=none) header.from= Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1564508700220325.36318630416963; Tue, 30 Jul 2019 10:45:00 -0700 (PDT) Received: from localhost ([::1]:35286 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.86_2) (envelope-from ) id 1hsWBH-00066v-7l for importer@patchew.org; Tue, 30 Jul 2019 13:44:59 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:35714) by lists.gnu.org with esmtp (Exim 4.86_2) (envelope-from ) id 1hsW2n-0005AK-HV for qemu-devel@nongnu.org; Tue, 30 Jul 2019 13:36:14 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1hsW2l-0000Iz-Ph for qemu-devel@nongnu.org; Tue, 30 Jul 2019 13:36:13 -0400 Received: from mail-pg1-x544.google.com ([2607:f8b0:4864:20::544]:33701) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1hsW2j-0000IC-3s; Tue, 30 Jul 2019 13:36:11 -0400 Received: by mail-pg1-x544.google.com with SMTP id f20so21195355pgj.0; Tue, 30 Jul 2019 10:36:09 -0700 (PDT) Received: from localhost.localdomain ([136.233.9.97]) by smtp.gmail.com with ESMTPSA id q24sm59122895pjp.14.2019.07.30.10.36.02 (version=TLS1_3 cipher=AEAD-AES256-GCM-SHA384 bits=256/256); Tue, 30 Jul 2019 10:36:07 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=VIbCCiqkXwkRR3OlBzyvEa8q9jsIq4iRUCXYKqboH9I=; b=XJdxCO1WiNG7haTrUsFKhB6QVaJv2Eo4LghlqaQPjJUiFl+pVWiqvPaSwsBrMZGBbo FqgHbZbROmy8hGVK9tx2/xv8++wOfi2pnoUWKKNsVz10wVXvccsVYwjWG94hVTjsI6is Gfp7vOB63mOkUAWH9mWM50LDvFgAaz4Pu5iSEi9rvoJgOtldwqFBWQfoWbSj+7+3jBie grCylFl1cMUCeovhqd6h6lAyPC/bXOmSbAA9Blzqf6c+9t5B8bJ1tWln2QgV6IsuK9Bm 3HWXS5Ki6mAx/dX0SoR1e0lfFaWl4PcakydgDFfA176cmuffLWXwfkXKMGBW2TmKF99S JKfA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=VIbCCiqkXwkRR3OlBzyvEa8q9jsIq4iRUCXYKqboH9I=; b=q5ZwMoY+UnD9Re/169/4xfgGUsr8o/mgd07X1ojxfsKrMVZaYzmGBQhWAcxuOsKDn0 yqlZ36/jhH1aC6zW7z9Ybx9XI0KyC58FvNnxwhamPaxQE3Syw1l1trj7VqcMd5mClELr 3oO2uRc21+eD3RrEWZwg7JcVMWi9Ctz0ySKQ7lqozccIoWBrnsdazOtk9eh7sbMgl7Tz bATRXZ6BIo8EMvEZF+HnGCSij0Gzz3POpyVTM+TQicyyk7zKgWSTyjNQGUoF1DTOQJ+E /AxOMsSYwuQqItK7M/UAzT8AtykrvFRgyx2Y2g2eluN7wicFIVg2KPbaneEAyEuZ+g56 vQEQ== X-Gm-Message-State: APjAAAXdxsqKAktm5jaXkvlBrHVXlppcixSHFFax2o3G/7vx/X+9THI4 3CbB13TWoWE89BqLGo3WK0mQUYnWGsrYjg== X-Google-Smtp-Source: APXvYqy+eiQlA+yWiCZKa7wL+ahjjhY+peGsf/z9SL3jbtpI723aTLAhtZSXaRvO1/Il6JzuJ5XIPw== X-Received: by 2002:a63:d84e:: with SMTP id k14mr110248982pgj.234.1564508167632; Tue, 30 Jul 2019 10:36:07 -0700 (PDT) From: Aarushi Mehta To: qemu-devel@nongnu.org Date: Tue, 30 Jul 2019 23:04:33 +0530 Message-Id: <20190730173441.26486-9-mehta.aaru20@gmail.com> X-Mailer: git-send-email 2.21.0 In-Reply-To: <20190730173441.26486-1-mehta.aaru20@gmail.com> References: <20190730173441.26486-1-mehta.aaru20@gmail.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2607:f8b0:4864:20::544 Subject: [Qemu-devel] [PATCH v8 08/16] block/file-posix.c: extend to use io_uring X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Kevin Wolf , Fam Zheng , Sergio Lopez , qemu-block@nongnu.org, Markus Armbruster , Maxim Levitsky , saket.sinha89@gmail.com, Max Reitz , Stefan Hajnoczi , Paolo Bonzini , Stefan Hajnoczi , Julia Suvorova , Aarushi Mehta , Maxim Levitsky Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail-DKIM: fail (Header signature does not verify) Content-Type: text/plain; charset="utf-8" Signed-off-by: Aarushi Mehta Reviewed-by: Stefan Hajnoczi Reviewed-by: Maxim Levitsky --- block/file-posix.c | 99 ++++++++++++++++++++++++++++++++++++---------- 1 file changed, 79 insertions(+), 20 deletions(-) diff --git a/block/file-posix.c b/block/file-posix.c index 4479cc7ab4..4aa42f826f 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -156,6 +156,7 @@ typedef struct BDRVRawState { bool has_write_zeroes:1; bool discard_zeroes:1; bool use_linux_aio:1; + bool use_linux_io_uring:1; bool page_cache_inconsistent:1; bool has_fallocate; bool needs_alignment; @@ -425,7 +426,7 @@ static QemuOptsList raw_runtime_opts =3D { { .name =3D "aio", .type =3D QEMU_OPT_STRING, - .help =3D "host AIO implementation (threads, native)", + .help =3D "host AIO implementation (threads, native, io_uring)= ", }, { .name =3D "locking", @@ -484,9 +485,15 @@ static int raw_open_common(BlockDriverState *bs, QDict= *options, goto fail; } =20 - aio_default =3D (bdrv_flags & BDRV_O_NATIVE_AIO) - ? BLOCKDEV_AIO_OPTIONS_NATIVE - : BLOCKDEV_AIO_OPTIONS_THREADS; + if (bdrv_flags & BDRV_O_NATIVE_AIO) { + aio_default =3D BLOCKDEV_AIO_OPTIONS_NATIVE; +#ifdef CONFIG_LINUX_IO_URING + } else if (bdrv_flags & BDRV_O_IO_URING) { + aio_default =3D BLOCKDEV_AIO_OPTIONS_IO_URING; +#endif + } else { + aio_default =3D BLOCKDEV_AIO_OPTIONS_THREADS; + } aio =3D qapi_enum_parse(&BlockdevAioOptions_lookup, qemu_opt_get(opts, "aio"), aio_default, &local_err); @@ -495,7 +502,11 @@ static int raw_open_common(BlockDriverState *bs, QDict= *options, ret =3D -EINVAL; goto fail; } + s->use_linux_aio =3D (aio =3D=3D BLOCKDEV_AIO_OPTIONS_NATIVE); +#ifdef CONFIG_LINUX_IO_URING + s->use_linux_io_uring =3D (aio =3D=3D BLOCKDEV_AIO_OPTIONS_IO_URING); +#endif =20 locking =3D qapi_enum_parse(&OnOffAuto_lookup, qemu_opt_get(opts, "locking"), @@ -559,7 +570,7 @@ static int raw_open_common(BlockDriverState *bs, QDict = *options, s->shared_perm =3D BLK_PERM_ALL; =20 #ifdef CONFIG_LINUX_AIO - /* Currently Linux does AIO only for files opened with O_DIRECT */ + /* Currently Linux does AIO only for files opened with O_DIRECT */ if (s->use_linux_aio) { if (!(s->open_flags & O_DIRECT)) { error_setg(errp, "aio=3Dnative was specified, but it requires " @@ -581,6 +592,22 @@ static int raw_open_common(BlockDriverState *bs, QDict= *options, } #endif /* !defined(CONFIG_LINUX_AIO) */ =20 +#ifdef CONFIG_LINUX_IO_URING + if (s->use_linux_io_uring) { + if (!aio_setup_linux_io_uring(bdrv_get_aio_context(bs), errp)) { + error_prepend(errp, "Unable to use io_uring: "); + goto fail; + } + } +#else + if (s->use_linux_io_uring) { + error_setg(errp, "aio=3Dio_uring was specified, but is not support= ed " + "in this build."); + ret =3D -EINVAL; + goto fail; + } +#endif /* !defined(CONFIG_LINUX_IO_URING) */ + s->has_discard =3D true; s->has_write_zeroes =3D true; if ((bs->open_flags & BDRV_O_NOCACHE) !=3D 0) { @@ -1874,21 +1901,25 @@ static int coroutine_fn raw_co_prw(BlockDriverState= *bs, uint64_t offset, return -EIO; =20 /* - * Check if the underlying device requires requests to be aligned, - * and if the request we are trying to submit is aligned or not. - * If this is the case tell the low-level driver that it needs - * to copy the buffer. + * When using O_DIRECT, the request must be aligned to be able to use + * either libaio or io_uring interface. If not fail back to regular th= read + * pool read/write code which emulates this for us if we + * set QEMU_AIO_MISALIGNED. */ - if (s->needs_alignment) { - if (!bdrv_qiov_is_aligned(bs, qiov)) { - type |=3D QEMU_AIO_MISALIGNED; + if (s->needs_alignment && !bdrv_qiov_is_aligned(bs, qiov)) { + type |=3D QEMU_AIO_MISALIGNED; +#ifdef CONFIG_LINUX_IO_URING + } else if (s->use_linux_io_uring) { + LuringState *aio =3D aio_get_linux_io_uring(bdrv_get_aio_context(b= s)); + assert(qiov->size =3D=3D bytes); + return luring_co_submit(bs, aio, s->fd, offset, qiov, type); +#endif #ifdef CONFIG_LINUX_AIO - } else if (s->use_linux_aio) { - LinuxAioState *aio =3D aio_get_linux_aio(bdrv_get_aio_context(= bs)); - assert(qiov->size =3D=3D bytes); - return laio_co_submit(bs, aio, s->fd, offset, qiov, type); + } else if (s->use_linux_aio) { + LinuxAioState *aio =3D aio_get_linux_aio(bdrv_get_aio_context(bs)); + assert(qiov->size =3D=3D bytes); + return laio_co_submit(bs, aio, s->fd, offset, qiov, type); #endif - } } =20 acb =3D (RawPosixAIOData) { @@ -1924,24 +1955,36 @@ static int coroutine_fn raw_co_pwritev(BlockDriverS= tate *bs, uint64_t offset, =20 static void raw_aio_plug(BlockDriverState *bs) { + BDRVRawState __attribute__((unused)) *s =3D bs->opaque; #ifdef CONFIG_LINUX_AIO - BDRVRawState *s =3D bs->opaque; if (s->use_linux_aio) { LinuxAioState *aio =3D aio_get_linux_aio(bdrv_get_aio_context(bs)); laio_io_plug(bs, aio); } #endif +#ifdef CONFIG_LINUX_IO_URING + if (s->use_linux_io_uring) { + LuringState *aio =3D aio_get_linux_io_uring(bdrv_get_aio_context(b= s)); + luring_io_plug(bs, aio); + } +#endif } =20 static void raw_aio_unplug(BlockDriverState *bs) { + BDRVRawState __attribute__((unused)) *s =3D bs->opaque; #ifdef CONFIG_LINUX_AIO - BDRVRawState *s =3D bs->opaque; if (s->use_linux_aio) { LinuxAioState *aio =3D aio_get_linux_aio(bdrv_get_aio_context(bs)); laio_io_unplug(bs, aio); } #endif +#ifdef CONFIG_LINUX_IO_URING + if (s->use_linux_io_uring) { + LuringState *aio =3D aio_get_linux_io_uring(bdrv_get_aio_context(b= s)); + luring_io_unplug(bs, aio); + } +#endif } =20 static int raw_co_flush_to_disk(BlockDriverState *bs) @@ -1961,14 +2004,20 @@ static int raw_co_flush_to_disk(BlockDriverState *b= s) .aio_type =3D QEMU_AIO_FLUSH, }; =20 +#ifdef CONFIG_LINUX_IO_URING + if (s->use_linux_io_uring) { + LuringState *aio =3D aio_get_linux_io_uring(bdrv_get_aio_context(b= s)); + return luring_co_submit(bs, aio, s->fd, 0, NULL, QEMU_AIO_FLUSH); + } +#endif return raw_thread_pool_submit(bs, handle_aiocb_flush, &acb); } =20 static void raw_aio_attach_aio_context(BlockDriverState *bs, AioContext *new_context) { + BDRVRawState __attribute__((unused)) *s =3D bs->opaque; #ifdef CONFIG_LINUX_AIO - BDRVRawState *s =3D bs->opaque; if (s->use_linux_aio) { Error *local_err; if (!aio_setup_linux_aio(new_context, &local_err)) { @@ -1978,6 +2027,16 @@ static void raw_aio_attach_aio_context(BlockDriverSt= ate *bs, } } #endif +#ifdef CONFIG_LINUX_IO_URING + if (s->use_linux_io_uring) { + Error *local_err; + if (!aio_setup_linux_io_uring(new_context, &local_err)) { + error_reportf_err(local_err, "Unable to use linux io_uring, " + "falling back to thread pool: "); + s->use_linux_io_uring =3D false; + } + } +#endif } =20 static void raw_close(BlockDriverState *bs) --=20 2.21.0