From patchwork Sun Sep 1 13:37:07 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Bernd Schubert X-Patchwork-Id: 13786486 Received: from outbound-ip168a.ess.barracuda.com (outbound-ip168a.ess.barracuda.com [209.222.82.36]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 3075014A4FF for ; Sun, 1 Sep 2024 14:11:59 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=fail smtp.client-ip=209.222.82.36 ARC-Seal: i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1725199922; cv=fail; b=ksknuTgSpkns4zjtrKwfw/lGqBYB4wQ+ojgGpqAMr3b86HVoobbXj3fhHIrgfnfE6/nEh0VZNemgEAUlCa0XMKrTNOFiuY0MIy4ZZoCRAzBgbu1FLNi+qK+Su1BXToXDHjOjF44gyF8/Or5S29yP2y5dNycU+UjEDD6NCqHuvnI= ARC-Message-Signature: i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1725199922; c=relaxed/simple; bh=48GPYOKOv8QstAokuDa8NlonP/TjSLahD8Y3o5cLiWU=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=i83ezMBwGVSMuTedjkJJo8SWgTWnzgCetlMbeGQryMbiP3mhIgv1l5AwVDOsaFhdVD32s24OFBfUzFRO02KmrAShHQof6pGMQcqG74KQ5ylbiSn1e2eh1TNhIzuk7qPEEB7an50thCUyd4n/h3+CqAFgniABf1C0oB706+2L3NA= ARC-Authentication-Results: i=2; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=ddn.com; spf=pass smtp.mailfrom=ddn.com; dkim=pass (1024-bit key) header.d=ddn.com header.i=@ddn.com header.b=1k0DCccb; arc=fail smtp.client-ip=209.222.82.36 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=ddn.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=ddn.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=ddn.com header.i=@ddn.com header.b="1k0DCccb" Received: from NAM02-BN1-obe.outbound.protection.outlook.com (mail-bn1nam02lp2040.outbound.protection.outlook.com [104.47.51.40]) by mx-outbound45-16.us-east-2c.ess.aws.cudaops.com (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO); Sun, 01 Sep 2024 14:11:58 +0000 ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=LGldjW+pdnw382ICfhaKojonegL6xgGsl5HOIfTR7XJVyhH9NmYZOMlG4xdMF1GSMs1CIq+9OoM5pPIBGvnClNPU0iuC/TVg2xXDll8ZuQuzUTLn/ofXg4mh00Ei6XlI3z8yp3EqR/29FsKicvIhRmJqnKM30l9g98Pm9Q/LDcw/wqR9UzmVtMlmKrjWwDaKy+xxHmvLqaaej+PEH+7MHY62Vqe2hqnupS2QMWiyWJyr2Xyj4MKpQ4B24ZRQN1/WPvVaWNXAvcGCdcqoeC4WV6MRlm729RsWQIBVy7jkfV8EjG5kkSELMM4KPjcPWs8+v5qdBhnGHNlTd6jXHKLG5g== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=HQOtdUiFVUeg27JJdVwU6S2ZUaMwoGj91RAVXoW+FYo=; b=ig0pHTD2DAeGozWCnV8QM5ewQGfQRB7Uf+aO67YIwxD4qD8x4rYzX2DC9zu6HyNk5zMT9ek+QgOUpFTV2vZxuzfegncjrkn/VcHgqrRQa0rIvWWeCroyskuZbcKIN6stlzGBq3MymGk1vWxZFdAisqEPaypuPhJ4ORKlZP3KH/D5u9F39WOnP97ZARYYwo/A7JHqHJDGz6k5j/Pt10BCbqDYh5gDCyUL6RBCDPh4Bga3txstC7N8G61E9pD7D4C/waJ5lwSvVbKH4c1j+uohqDhWW6p/R0E4EJBN0iDVy56kG+yyguebFb3ZgO7FbjeVdiXsN8b4GUODmLf8twaI9w== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass (sender ip is 50.222.100.11) smtp.rcpttodomain=ddn.com smtp.mailfrom=ddn.com; dmarc=pass (p=reject sp=reject pct=100) action=none header.from=ddn.com; dkim=none (message not signed); arc=none (0) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ddn.com; s=selector2; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=HQOtdUiFVUeg27JJdVwU6S2ZUaMwoGj91RAVXoW+FYo=; b=1k0DCccbhRsrIs88UJmI0oQmqGpZjxw88FiMcUawoV4fgK1kUmF8VM/J7pFPaUEYlc3MeQ19VAcx0vfUUtGelled/QCByfyHcWx2qE8BHhK+q6vzGKLrjvqsLIXENVaAT5jVk9rDEQmmg3wxcig64jI9YiZT8YaLbiRBFXdUPNA= Received: from SJ0PR05CA0081.namprd05.prod.outlook.com (2603:10b6:a03:332::26) by PH7PR19MB5750.namprd19.prod.outlook.com (2603:10b6:510:1d1::16) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.7918.23; Sun, 1 Sep 2024 13:37:11 +0000 Received: from SJ5PEPF000001CA.namprd05.prod.outlook.com (2603:10b6:a03:332:cafe::b4) by SJ0PR05CA0081.outlook.office365.com (2603:10b6:a03:332::26) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.7918.24 via Frontend Transport; Sun, 1 Sep 2024 13:37:11 +0000 X-MS-Exchange-Authentication-Results: spf=pass (sender IP is 50.222.100.11) smtp.mailfrom=ddn.com; dkim=none (message not signed) header.d=none;dmarc=pass action=none header.from=ddn.com; Received-SPF: Pass (protection.outlook.com: domain of ddn.com designates 50.222.100.11 as permitted sender) receiver=protection.outlook.com; client-ip=50.222.100.11; helo=uww-mrp-01.datadirectnet.com; pr=C Received: from uww-mrp-01.datadirectnet.com (50.222.100.11) by SJ5PEPF000001CA.mail.protection.outlook.com (10.167.242.39) with Microsoft SMTP Server (version=TLS1_3, cipher=TLS_AES_256_GCM_SHA384) id 15.20.7918.13 via Frontend Transport; Sun, 1 Sep 2024 13:37:10 +0000 Received: from localhost (unknown [10.68.0.8]) by uww-mrp-01.datadirectnet.com (Postfix) with ESMTP id 4B26372; Sun, 1 Sep 2024 13:37:10 +0000 (UTC) From: Bernd Schubert Date: Sun, 01 Sep 2024 15:37:07 +0200 Subject: [PATCH RFC v3 13/17] fuse: {uring} Add a ring queue and send method Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Message-Id: <20240901-b4-fuse-uring-rfcv3-without-mmap-v3-13-9207f7391444@ddn.com> References: <20240901-b4-fuse-uring-rfcv3-without-mmap-v3-0-9207f7391444@ddn.com> In-Reply-To: <20240901-b4-fuse-uring-rfcv3-without-mmap-v3-0-9207f7391444@ddn.com> To: Miklos Szeredi , Jens Axboe , Pavel Begunkov , bernd@fastmail.fm Cc: linux-fsdevel@vger.kernel.org, io-uring@vger.kernel.org, Joanne Koong , Josef Bacik , Amir Goldstein , Bernd Schubert X-Mailer: b4 0.14.1 X-Developer-Signature: v=1; a=ed25519-sha256; t=1725197817; l=4710; i=bschubert@ddn.com; s=20240529; h=from:subject:message-id; bh=48GPYOKOv8QstAokuDa8NlonP/TjSLahD8Y3o5cLiWU=; b=UScpLiDFoG2eYQJr7xRap+gaF572Z5o5JdLBVXHRhwA0nNLk6nQcaPDaFp6Z2C6+SUNNKCA5F /WvOtmURGw8DbDogm7V/S+NYAVTsELyHp8rnOFa0dy+KhUeW6wgBiCE X-Developer-Key: i=bschubert@ddn.com; a=ed25519; pk=EZVU4bq64+flgoWFCVQoj0URAs3Urjno+1fIq9ZJx8Y= X-EOPAttributedMessage: 0 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: SJ5PEPF000001CA:EE_|PH7PR19MB5750:EE_ X-MS-Office365-Filtering-Correlation-Id: c1acfc8e-f83d-40df-0479-08dcca8b2e9b X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam: BCL:0;ARA:13230040|1800799024|36860700013|376014|82310400026; X-Microsoft-Antispam-Message-Info: =?utf-8?q?WkPuJsYbDTXOKimlgGAAtOFKaiJh7oQ?= =?utf-8?q?OZddEx1hyiqDxVK9yk6ZmwAFabqGzu8+YJlH8crEsQytpWhq85ahIkVJOYx7V2gbk?= =?utf-8?q?7tzhygVmQhQjORPCnIjKL/hhUyMDm/SkOLWtpDjeza8XiVti8ybExe1ywVSZkWIRu?= =?utf-8?q?x3iZ4/bOpMmySzATFgWl33r76RKo12m3AvIxCOJuATyy8DpT2VpQKgdn1NVG74GJj?= =?utf-8?q?IbICj1a/Hbw3IE6+Cd6KTeDU+cvfC5gmzRk+8J/JSnm80nr3TAiUXL/nhy2v2Xf9m?= =?utf-8?q?617hK7GWLvh40gADjgl/3olYFtckOTW9RHykf2HtM5D/95X9xDbrrhB0bzVGK2hN1?= =?utf-8?q?am5g4jYq21Aor6rdF6DtR1XP0O1JriIHIb3jJDU0kT8vcUecBJCjkO2RAmg7Up7vZ?= =?utf-8?q?u4tZJsv0C6n09jrPXdBKGrOSAA18jJJLPmlWmJCjMAN5MSB6YKJYbhncwNhq7srVH?= =?utf-8?q?fWU2VNH4s9CeoZM5JZEgdfq/hjJV/OwKg9boQnslofQBxl8Ny8PXRGXvCla0KikMa?= =?utf-8?q?p6QBOkJs5T1/18XQAD2+dI01CdJEhFTBp/AFkMqysbb85VEoxYt9kwLfadcd54UP6?= =?utf-8?q?USYT1Do27o73BIYNq80zcf6A0B4yG4LvBzptFc+Xc4dzZDFEFNLj6+zgf5pOzJrsc?= =?utf-8?q?mChluS3woKweYDETc8YMiKfvX/1HG5kYe4fEDYa8Q9iThd40PhtiVFqAjA5ma1Fgs?= =?utf-8?q?a5HUnLf6AioyQ7bHvQtl8ufTMX0kB13UbpyeSItKw8U0hjcqPxPASHjV3sxd3agNg?= =?utf-8?q?hDpD1xOsszJONubtX+bnpfR57cv4zEYG1qxdFOPu00fqCIqe9BepjdK0mm9oYh0lY?= =?utf-8?q?wzQdgAU42TpYB9R+N19frEvYMSPt1f2Mz9sYjSeItDk/heo3sVYngAVi0GMbOVIaf?= =?utf-8?q?nlUQPYjS0YrhPRNw4REDbf1zhsiWWsxMb7pijTbB5F7DS6kEUFtVd+h7ljqVjVkg5?= =?utf-8?q?rWvFkkJ3flw9Fe01uXXYewzRDRItE7/AuPCeHMsA/PE9aBJMsoFQY61jeKd2KldYu?= =?utf-8?q?LmjRL7Ybl0NCsYvA1NL+xOM27lUD6r/13n1xkeB6l7xaBiFQi/IsET+pjFzEV0C6I?= =?utf-8?q?RaDyZavels0XrvRBSbpF0x/lPQI3OiPl5K6FUi6DG2Xf4bZmoCHbhHv+h0I8XtqVT?= =?utf-8?q?si5uoidpHJtKjwvR5Xwdobhxt6ZhCGCKH0PM3nvji1hbwA4TtaMzLGqDHtSPJpl52?= =?utf-8?q?sFsqYlwRkO01I5uNi23E0+7iZBvcprHJSdz74DvsHlT9gOPN8ZPbJOZae3fTvVy0x?= =?utf-8?q?7NdyZxESGPWiN46YFaG8EyKjkBlo/iEXGHMhctMyGBFYZMK9nONnSv7h2sXRZbUFu?= =?utf-8?q?4qnXzbOaiPMQVMvaMy8kNhboenq0RVO2iqxTv/vXrAtVWUJQHVgnB+GuGFKO4uTn7?= =?utf-8?q?sQbPF5rYXzk?= X-Forefront-Antispam-Report: CIP:50.222.100.11;CTRY:US;LANG:en;SCL:1;SRV:;IPV:NLI;SFV:NSPM;H:uww-mrp-01.datadirectnet.com;PTR:InfoDomainNonexistent;CAT:NONE;SFS:(13230040)(1800799024)(36860700013)(376014)(82310400026);DIR:OUT;SFP:1102; X-MS-Exchange-AntiSpam-ExternalHop-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-ExternalHop-MessageData-0: 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 X-MS-Exchange-CrossTenant-OriginalArrivalTime: 01 Sep 2024 13:37:10.9850 (UTC) X-MS-Exchange-CrossTenant-Network-Message-Id: c1acfc8e-f83d-40df-0479-08dcca8b2e9b X-MS-Exchange-CrossTenant-Id: 753b6e26-6fd3-43e6-8248-3f1735d59bb4 X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=753b6e26-6fd3-43e6-8248-3f1735d59bb4;Ip=[50.222.100.11];Helo=[uww-mrp-01.datadirectnet.com] X-MS-Exchange-CrossTenant-AuthSource: SJ5PEPF000001CA.namprd05.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Anonymous X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem X-MS-Exchange-Transport-CrossTenantHeadersStamped: PH7PR19MB5750 X-OriginatorOrg: ddn.com X-BESS-ID: 1725199918-111536-13527-71134-1 X-BESS-VER: 2019.1_20240829.0001 X-BESS-Apparent-Source-IP: 104.47.51.40 X-BESS-Parts: H4sIAAAAAAACA4uuVkqtKFGyUioBkjpK+cVKViamZsZAVgZQ0CzNwjjJNNHSwN IiMTkxxcLSLC0xzTLFwNzAIs0wNclSqTYWALB0aLpBAAAA X-BESS-Outbound-Spam-Score: 0.00 X-BESS-Outbound-Spam-Report: Code version 3.2, rules version 3.2.2.258744 [from cloudscan22-227.us-east-2b.ess.aws.cudaops.com] Rule breakdown below pts rule name description ---- ---------------------- -------------------------------- 0.00 BSF_BESS_OUTBOUND META: BESS Outbound 0.00 BSF_SC0_MISMATCH_TO META: Envelope rcpt doesn't match header X-BESS-Outbound-Spam-Status: SCORE=0.00 using account:ESS124931 scores of KILL_LEVEL=7.0 tests=BSF_BESS_OUTBOUND, BSF_SC0_MISMATCH_TO X-BESS-BRTS-Status: 1 This prepares queueing and sending through io-uring. Signed-off-by: Bernd Schubert --- fs/fuse/dev_uring.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++++++ fs/fuse/dev_uring_i.h | 7 ++++ 2 files changed, 111 insertions(+) diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c index 52e2323cc258..43e7486d9f93 100644 --- a/fs/fuse/dev_uring.c +++ b/fs/fuse/dev_uring.c @@ -975,3 +975,107 @@ int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) spin_unlock(&queue->lock); goto out; } + +/* + * This prepares and sends the ring request in fuse-uring task context. + * User buffers are not mapped yet - the application does not have permission + * to write to it - this has to be executed in ring task context. + * XXX: Map and pin user paged and avoid this function. + */ +static void +fuse_uring_send_req_in_task(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + struct fuse_uring_cmd_pdu *pdu = (struct fuse_uring_cmd_pdu *)cmd->pdu; + struct fuse_ring_ent *ring_ent = pdu->ring_ent; + struct fuse_ring_queue *queue = ring_ent->queue; + int err; + + BUILD_BUG_ON(sizeof(pdu) > sizeof(cmd->pdu)); + + err = fuse_uring_prepare_send(ring_ent); + if (err) + goto err; + + io_uring_cmd_done(cmd, 0, 0, issue_flags); + + spin_lock(&queue->lock); + ring_ent->state = FRRS_USERSPACE; + list_add(&ring_ent->list, &queue->ent_in_userspace); + spin_unlock(&queue->lock); + + return; +err: + fuse_uring_next_fuse_req(ring_ent, queue); +} + +/* queue a fuse request and send it if a ring entry is available */ +int fuse_uring_queue_fuse_req(struct fuse_conn *fc, struct fuse_req *req) +{ + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + int qid = 0; + struct fuse_ring_ent *ring_ent = NULL; + int res; + bool async = test_bit(FR_BACKGROUND, &req->flags); + struct list_head *req_queue, *ent_queue; + + if (ring->per_core_queue) { + /* + * async requests are best handled on another core, the current + * core can do application/page handling, while the async request + * is handled on another core in userspace. + * For sync request the application has to wait - no processing, so + * the request should continue on the current core and avoid context + * switches. + * XXX This should be on the same numa node and not busy - is there + * a scheduler function available that could make this decision? + * It should also not persistently switch between cores - makes + * it hard for the scheduler. + */ + qid = task_cpu(current); + + if (WARN_ONCE(qid >= ring->nr_queues, + "Core number (%u) exceeds nr ueues (%zu)\n", + qid, ring->nr_queues)) + qid = 0; + } + + queue = fuse_uring_get_queue(ring, qid); + req_queue = async ? &queue->async_fuse_req_queue : + &queue->sync_fuse_req_queue; + ent_queue = async ? &queue->async_ent_avail_queue : + &queue->sync_ent_avail_queue; + + spin_lock(&queue->lock); + + if (unlikely(queue->stopped)) { + res = -ENOTCONN; + goto err_unlock; + } + + list_add_tail(&req->list, req_queue); + + if (!list_empty(ent_queue)) { + ring_ent = + list_first_entry(ent_queue, struct fuse_ring_ent, list); + list_del_init(&ring_ent->list); + fuse_uring_add_req_to_ring_ent(ring_ent, req); + } + spin_unlock(&queue->lock); + + if (ring_ent != NULL) { + struct io_uring_cmd *cmd = ring_ent->cmd; + struct fuse_uring_cmd_pdu *pdu = + (struct fuse_uring_cmd_pdu *)cmd->pdu; + + pdu->ring_ent = ring_ent; + io_uring_cmd_complete_in_task(cmd, fuse_uring_send_req_in_task); + } + + return 0; + +err_unlock: + spin_unlock(&queue->lock); + return res; +} diff --git a/fs/fuse/dev_uring_i.h b/fs/fuse/dev_uring_i.h index 432465d4bfce..d9988d4beeed 100644 --- a/fs/fuse/dev_uring_i.h +++ b/fs/fuse/dev_uring_i.h @@ -176,6 +176,7 @@ void fuse_uring_abort_end_requests(struct fuse_ring *ring); int fuse_uring_conn_cfg(struct file *file, void __user *argp); void fuse_uring_stop_queues(struct fuse_ring *ring); int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags); +int fuse_uring_queue_fuse_req(struct fuse_conn *fc, struct fuse_req *req); static inline void fuse_uring_conn_destruct(struct fuse_conn *fc) { @@ -293,6 +294,12 @@ static inline void fuse_uring_abort(struct fuse_conn *fc) static inline void fuse_uring_wait_stopped_queues(struct fuse_conn *fc) { } + +static inline int +fuse_uring_queue_fuse_req(struct fuse_conn *fc, struct fuse_req *req) +{ + return -EPFNOSUPPORT; +} #endif /* CONFIG_FUSE_IO_URING */ #endif /* _FS_FUSE_DEV_URING_I_H */