From patchwork Tue Oct 29 15:16:30 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855086 Received: from mail-io1-f44.google.com (mail-io1-f44.google.com [209.85.166.44]) (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 01F9419309C for ; Tue, 29 Oct 2024 15:23:04 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.44 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215388; cv=none; b=r0wsOlRRPmFZIjbv/uzp1iBMVpv1PxhSYVJ6APBIaTWYKdNnUSY9VdXqVE+emmtOWWhxyXs5SN0XPJrgunt1dUaE7Pi49+4k/qKQfj7wXgj6HAvTr36ukVDs9qKkp/oTkQblQG23mWAv0fGNNn6dsckZ2cB8AB6LJkZev8lxOGA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215388; c=relaxed/simple; bh=HPnvI+rOjDAWZqF0Xd42uWJKF/3qtcinc1VyXx9MXy4=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=VGdM4yjZiB9djoecLwIWDbrFUgIrRLiBdxa0q5/9lbwgXHDBBGPHBNqsNDnQt4Q2wUDJ0kh0ue+wObiMzie5H93N1G7MpyIYHg0XmlCAFewo4CyYvLMycpka8jJ/tLEEX/J/h4t5BbRav4+qyBWds6xQ5Jb9hKtvuHmQLOmsaVQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=vsnu8H3X; arc=none smtp.client-ip=209.85.166.44 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="vsnu8H3X" Received: by mail-io1-f44.google.com with SMTP id ca18e2360f4ac-83abe7fc77eso216129039f.0 for ; Tue, 29 Oct 2024 08:23:04 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215384; x=1730820184; darn=vger.kernel.org; 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=lk/+RVPeoujW1QBGROEzXF5c7w5OPLyPUXaokbUSoj0=; b=vsnu8H3XVuEqFy4VIR4JsaiT55+p2IlwtQriRvLxypjhuWpsyjjjJqn9jtAuGvdC0x CLAp9ColUzJ1I9iColhO5X6qldvFnPj+BXUu4S0CNppc0MEMnc86Sc+A/bp/2owjvjHC L0pQR1sKae/ocYh/oQQFc63GvO4TC0bk0x6UL37KNt9gFXOGgiFlsiHG43przn3LLRRd D4Q2hpTl7smFzSsk5GAfeIpdk+lLUfBKmZrSwsbfOfRlQySLEj3n2RGA4avwCXR9fjL5 3JIL1zYsyB+EuzZipm10KusVsj1KT1+2ZnrnzWw6rANn08ah+aeVQSZJAYRNz+AFiFTA fKJg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215384; x=1730820184; 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=lk/+RVPeoujW1QBGROEzXF5c7w5OPLyPUXaokbUSoj0=; b=s1lCXZkU6553ezwsF784gvWjnPg7W8MU/6jBeCoCnVKLVzMkcMgOt17pVm1PYi8xZE o8f7aMg6Ka2j1N0r15TE11rMJJ6Cy4MjHprTPum7Q3aq/SP5sGFU4EQf0SC6jzpBlshN PrLocnDcLlvexdmYPtt9bewdqJss+T3WCqNhH05m78BhoMeR3d5KU4ZabcOpCiYXSyFS 5JgVlNsG5hxGUAli0Wf8LlED9pVFmiP6b+DOCTJgts9uopAHMccYY4WmQ6C9t37xXprg G1xIC2ROtzRRWOTxFcjBUd1I1ts9kFofyphDNxPmCh8DmDqADzyQ6j97q/Nx0twZg82T cR5g== X-Gm-Message-State: AOJu0YzSvUryl+OUbjn5UMNc1ZkZu891/YHs1YVw6p+mqXk/NBX8PQUB fSJrPGWnPmCFksXGhky1GqB4IeUOEjZyyzlrGcMknkFcJKLF9tgkqwS+05g2T05Zz6B3uuBcbOs B X-Google-Smtp-Source: AGHT+IFyGCgj6sBqmq1H7Fa2+H7eo/7eyAqvIAEKnYZENz7KEfldBCmNDyOcpnBounuaDFLGHEk3yA== X-Received: by 2002:a05:6602:6102:b0:83b:5221:2a87 with SMTP id ca18e2360f4ac-83b52215d0cmr148735839f.3.1730215383557; Tue, 29 Oct 2024 08:23:03 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.02 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:02 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 01/14] io_uring/nop: add support for testing registered files and buffers Date: Tue, 29 Oct 2024 09:16:30 -0600 Message-ID: <20241029152249.667290-2-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Useful for testing performance/efficiency impact of registered files and buffers, vs (particularly) non-registered files. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 3 +++ io_uring/nop.c | 49 +++++++++++++++++++++++++++++++---- 2 files changed, 47 insertions(+), 5 deletions(-) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 65b7417c1b05..024745283783 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -416,6 +416,9 @@ enum io_uring_msg_ring_flags { * IORING_NOP_INJECT_RESULT Inject result from sqe->result */ #define IORING_NOP_INJECT_RESULT (1U << 0) +#define IORING_NOP_FILE (1U << 1) +#define IORING_NOP_FIXED_FILE (1U << 2) +#define IORING_NOP_FIXED_BUFFER (1U << 3) /* * IO completion data structure (Completion Queue Entry) diff --git a/io_uring/nop.c b/io_uring/nop.c index a5bcf3d6984f..2c7a22ba4053 100644 --- a/io_uring/nop.c +++ b/io_uring/nop.c @@ -8,35 +8,74 @@ #include #include "io_uring.h" +#include "rsrc.h" #include "nop.h" struct io_nop { /* NOTE: kiocb has the file as the first member, so don't do it here */ struct file *file; int result; + int fd; + int buffer; + unsigned int flags; }; +#define NOP_FLAGS (IORING_NOP_INJECT_RESULT | IORING_NOP_FIXED_FILE | \ + IORING_NOP_FIXED_BUFFER | IORING_NOP_FILE) + int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - unsigned int flags; struct io_nop *nop = io_kiocb_to_cmd(req, struct io_nop); - flags = READ_ONCE(sqe->nop_flags); - if (flags & ~IORING_NOP_INJECT_RESULT) + nop->flags = READ_ONCE(sqe->nop_flags); + if (nop->flags & ~NOP_FLAGS) return -EINVAL; - if (flags & IORING_NOP_INJECT_RESULT) + if (nop->flags & IORING_NOP_INJECT_RESULT) nop->result = READ_ONCE(sqe->len); else nop->result = 0; + if (nop->flags & IORING_NOP_FIXED_FILE) + nop->fd = READ_ONCE(sqe->fd); + if (nop->flags & IORING_NOP_FIXED_BUFFER) + nop->buffer = READ_ONCE(sqe->buf_index); return 0; } int io_nop(struct io_kiocb *req, unsigned int issue_flags) { struct io_nop *nop = io_kiocb_to_cmd(req, struct io_nop); + int ret = nop->result; + + if (nop->flags & IORING_NOP_FILE) { + if (nop->flags & IORING_NOP_FIXED_FILE) { + req->file = io_file_get_fixed(req, nop->fd, issue_flags); + req->flags |= REQ_F_FIXED_FILE; + } else { + req->file = io_file_get_normal(req, nop->fd); + } + if (!req->file) { + ret = -EBADF; + goto done; + } + } + if (nop->flags & IORING_NOP_FIXED_BUFFER) { + struct io_ring_ctx *ctx = req->ctx; + struct io_mapped_ubuf *imu; + int idx; - if (nop->result < 0) + ret = -EFAULT; + io_ring_submit_lock(ctx, issue_flags); + if (nop->buffer < ctx->nr_user_bufs) { + idx = array_index_nospec(nop->buffer, ctx->nr_user_bufs); + imu = READ_ONCE(ctx->user_bufs[idx]); + io_req_set_rsrc_node(req, ctx); + ret = 0; + } + io_ring_submit_unlock(ctx, issue_flags); + } +done: + if (ret < 0) req_set_fail(req); io_req_set_res(req, nop->result, 0); return IOU_OK; From patchwork Tue Oct 29 15:16:31 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855087 Received: from mail-io1-f42.google.com (mail-io1-f42.google.com [209.85.166.42]) (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 72E591946A2 for ; Tue, 29 Oct 2024 15:23:06 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.42 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215388; cv=none; b=El1SfcliEnG7Hqr7bpVqCr5Ibt7trJ6sRgcx9lanCQrD//1G2SPZGegld0E0RS+joi8l2DZv/41Pdqnp2sK7hp4Y0sU2+mdJ2Fdgqrk3QssxralkZ4UN/7EttUQ1vrUbT0t/PBA3T3EMYmOLEkuiencsfbYuRt56XvwMcZg1TVo= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215388; c=relaxed/simple; bh=gbtUQsMeQx/ihpjCfNEVueNKiMVBzIIvZfHP4mZ+ic0=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=cYJ2h8GrFlIcAk/Ggc75EnWDaAfdFmAogyiy0cZH133ch5ppf6nU3Tj8uHtxzBoUseJher8H3DNslWsw/eLLSCXrOZKKAVPFueCO7V/NtPigOKzEi5qRPkssI1T0YOqOnHIA0n7d00LRPiHT/agxqLlnpEgW8IuLA9srHIOzKrM= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=naAazT9i; arc=none smtp.client-ip=209.85.166.42 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="naAazT9i" Received: by mail-io1-f42.google.com with SMTP id ca18e2360f4ac-83ac4dacaf9so204319239f.2 for ; Tue, 29 Oct 2024 08:23:06 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215385; x=1730820185; darn=vger.kernel.org; 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=kWafocjdEh3Pob5N+inSXBHHJdCi0UP8BjhLCBT+Hd8=; b=naAazT9iqZHhEIyQnWk2PA9YzIao5ZYxuihcUC8yqAbGSI4Rx6l6tiIq7516IRe1+x c+BvG4vYBimT9CfKuu0SsbYKBV6y8QQshgqVplkJUXPG13yMdYWViwt2Tcdai/P31Vvu 2h+xYPo4UhgFSXZ1LukdikO8v1FSXp6J5toQJ23WmrOFuSdBwAdjo3DVM9m+uKOd30/2 /mq3rqhOYdXvtB2pGhvjs63M6se6z6oXgddeW4Q1ZDF1UaMHDhGHBvAREU3r160Pn1gO iM3ZCBlOtxJRez+P+AL2XtWRqdcKd31ujSaGOCBBD5uhnywgTq0/u5PYBdiRq8Gvg+qM hB1A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215385; x=1730820185; 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=kWafocjdEh3Pob5N+inSXBHHJdCi0UP8BjhLCBT+Hd8=; b=oarZFgXWGy88wz6ZVAnmZVpVVaQnCkiTjtQ9lh/g5/exLAO1KbgqAlHEKQqnqOIiSt UHFcyDOv9dSFVJGPVhYq19O61SQIJkMKlDsMlui1yFNaz/R/lf5+xxKtcx8ebWDktoP4 +M1v62vubVHSqEtjESVbgmufUnpD9qM90SbOCJpP+CsamJVmh2Np5gcfbHpWh4WNqCwE UEgdQz4XVQM8iV27lob9crkflk29d1uUjrDLg0QfWOwcsP8W0utjyiNT5l7uL1CvbKe4 8nYc7V7090k0XUR/OF8maRh78j0y+lDilDCKupeYxsbQNn7a5VRSnttVaN13wrDG/zKX gXYQ== X-Gm-Message-State: AOJu0YyQcKN+D0GBS0gv2fbmRsqMkSjW2rHHF2Rou8zWp5H061ozWNY+ AdJ01LC5CXuqm20tyjjy4uVGsAjNZIxRFyOE+cDTJOfSipegulKAEteyflyDSXFMl/jS5/wJLH2 / X-Google-Smtp-Source: AGHT+IEF57D2EsrbgHFGL1E7Ym3krPfmxeP8OuzrYyL7wqJ1uJgXkjmHDelNbiqPolBWIslX40BYhw== X-Received: by 2002:a05:6602:2c12:b0:83b:470d:bcdf with SMTP id ca18e2360f4ac-83b470dbd6cmr439571339f.13.1730215385093; Tue, 29 Oct 2024 08:23:05 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.03 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:03 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 02/14] io_uring/rsrc: move struct io_fixed_file to rsrc.h header Date: Tue, 29 Oct 2024 09:16:31 -0600 Message-ID: <20241029152249.667290-3-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 There's no need for this internal structure to be visible, move it to the private rsrc.h header instead. Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 5 ----- io_uring/filetable.h | 1 + io_uring/rsrc.h | 5 +++++ 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 2f12828b22a4..d4ba4ae480d6 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -55,11 +55,6 @@ struct io_wq_work { int cancel_seq; }; -struct io_fixed_file { - /* file * with additional FFS_* flags */ - unsigned long file_ptr; -}; - struct io_file_table { struct io_fixed_file *files; unsigned long *bitmap; diff --git a/io_uring/filetable.h b/io_uring/filetable.h index b2435c4dca1f..c027ed4ad68d 100644 --- a/io_uring/filetable.h +++ b/io_uring/filetable.h @@ -4,6 +4,7 @@ #include #include +#include "rsrc.h" bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files); void io_free_file_tables(struct io_file_table *table); diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index c50d4be4aa6d..e072fb3ee351 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -40,6 +40,11 @@ struct io_rsrc_node { struct io_rsrc_put item; }; +struct io_fixed_file { + /* file * with additional FFS_* flags */ + unsigned long file_ptr; +}; + struct io_mapped_ubuf { u64 ubuf; unsigned int len; From patchwork Tue Oct 29 15:16:32 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855088 Received: from mail-io1-f41.google.com (mail-io1-f41.google.com [209.85.166.41]) (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 DB8631946B9 for ; Tue, 29 Oct 2024 15:23:07 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.41 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215390; cv=none; b=cWxfgG6oG12nYrnWtwD3A1cxTrd9g3zbn3LbEM3vZhM/RH9q+0qC9rs6ZEp3FUizt0YvwS00sUV3R/z+R+CWgmcs+qhZi6hoYEErx2ROQylN8UaDC7frdqnA73vH5a04Pk6bAWg+aRDVkRCZapZRgAqs0X6ocHsWBhssEF3eEIM= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215390; c=relaxed/simple; bh=SYpQSxC5Dp9fLpjQdEWdmbvundwGSG12kF2zAC1HBac=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=opFkUgoC3IiAM/Vw98OtBCURxurrf9FfuwNB/7R72OpPQsLg1IZHCHLqvCP2VfWeH1XseklKPpo9BUyd+1pU/I/pQLBDnrRt/EmQRYG8G26RLevpRmnz3XeMgGw2RRjlPAqTIiHVb/oGWIsz8WFQojl7XcCYKINMMMjr4og7+tY= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=iglaf5zK; arc=none smtp.client-ip=209.85.166.41 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="iglaf5zK" Received: by mail-io1-f41.google.com with SMTP id ca18e2360f4ac-83a9be2c028so207842039f.1 for ; Tue, 29 Oct 2024 08:23:07 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215386; x=1730820186; darn=vger.kernel.org; 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=yp+EnMS7ATl15usRfPUg+8nUDFsAhh02UXOXNhYJd0A=; b=iglaf5zKAAZXNL8/03dh0l2Lg9bHnTNxLtvizY5NU8BUqipjE9GhVslzYkA3ZNBKLW iIzvs/IFcXXNJQSYmq8CeTZklwzURkQ1VTUSuMbosZ3MO1CcXsIrPvDy8/MQfPlZiaEf 4jBZ/t91OjxA7b4F04fdSnV8ZG7M/GrSSw34VtiWKbZ085elcK5b0gv8HnE4BL9P5MCj hdXQxuBwtDLSEUSBkmOQVxz7JMLAkXfJl1Jvqte9qNlsw2DQf7jM1TJUuaoGPuh/fIUV SyeDBriJhX7I7+qui5AgNDwVQfRbLWNHzCDolreisdZ9kSoIEhH+bsrGJr4ZZpbN6v4W bEKg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215386; x=1730820186; 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=yp+EnMS7ATl15usRfPUg+8nUDFsAhh02UXOXNhYJd0A=; b=Wx976K/B9jjTFfKcQbKG+WsZfADpb8fKiTcONuiC9PEjBLHM9ULnWt/4vWBKkyI4HL /SrDxL8bwdFSwRZjvig6HsI5qv9PvwMsL2GC0KQlO2ZWn6TmykpH3d9TpbBcEEjw6zhj z3+uWRPNDj9/T/a9khw7L9Ry/wRStF5HCNh8q2dPv/8tmQcNTI5YfOWkiQrO3chriu79 TZOsd+6QqbUC7aE4GVsJL1Lu6pbtrVEYJU6QlCrjDqm8bLC3eWzZNT2Q9nKDhl3BCsYP IjoBCqKxU9VbFiWitp3gOl6mI5wFr3KlcoPEKvVI2/3AWfqHEsmgP53XaNndIxcNBZi4 RYcQ== X-Gm-Message-State: AOJu0YyyL6ourRPflcy7Eg+q0c5RSg2FVdlVu340/E90NMGhwFP+UXMC P9xpvsh6Ad0Rkbi35NNc3bnGQy0Qq8+suHcugX3FMOejMVBjgABq2HW4db7znggjYzpnL8VzmZB M X-Google-Smtp-Source: AGHT+IEJbLL+ZwSlC6u3psE6EB7tU0uLx8tQYij3QYs9qbBKvXX6vrCJ8E6TNppb40gqX1f+s3csmA== X-Received: by 2002:a05:6602:2b01:b0:83a:b7e8:a684 with SMTP id ca18e2360f4ac-83b1c60b7d9mr1460896739f.11.1730215386535; Tue, 29 Oct 2024 08:23:06 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.05 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:05 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 03/14] io_uring: specify freeptr usage for SLAB_TYPESAFE_BY_RCU io_kiocb cache Date: Tue, 29 Oct 2024 09:16:32 -0600 Message-ID: <20241029152249.667290-4-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Doesn't matter right now as there's still some bytes left for it, but let's prepare for the io_kiocb potentially growing and add a specific freeptr offset for it. Signed-off-by: Jens Axboe Tested-by: Guenter Roeck --- io_uring/io_uring.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 2863b957e373..a09c67b38c1b 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3846,6 +3846,8 @@ static int __init io_uring_init(void) struct kmem_cache_args kmem_args = { .useroffset = offsetof(struct io_kiocb, cmd.data), .usersize = sizeof_field(struct io_kiocb, cmd.data), + .freeptr_offset = offsetof(struct io_kiocb, work), + .use_freeptr_offset = true, }; #define __BUILD_BUG_VERIFY_OFFSET_SIZE(stype, eoffset, esize, ename) do { \ From patchwork Tue Oct 29 15:16:33 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855089 Received: from mail-io1-f42.google.com (mail-io1-f42.google.com [209.85.166.42]) (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 3864A192D73 for ; Tue, 29 Oct 2024 15:23:09 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.42 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215391; cv=none; b=Ilh1eokxkhhd+GYVwhiK+WlxG8LMhlaGPq94R2Va+YYBGxl5VDd7OPq6YHmuEgxNT9A3J2BCJhF4kZ9sGU7fr0bgtgV28tWnP2m2rLXkk5LbtjTOt4R3Ay4agyMlAYlJmwTl/q9fmpchDlwO4mxAU7Ll/HXbbcIZeQJPy1qpbe8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215391; c=relaxed/simple; bh=MFnBn3Pt+fR8V94brBcdw32DLbRG+lgrEKVj+CSb2kM=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=u+vBdXVkqO0Gp5P/JgmIgtpXFgRG/ivD5ngdduSS+/VHM1Nu5ffg5GPGgi9jxScENtkFYzHifLoD+Dc54WchOV6Dtz2ixOgq0hj/8VKwhT6r/gGcDBTPXQIhYIBWuCSrUJboah3kMsA+l+CT4xCXaX3Qz2sNB76Jkof/AjkWCes= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=fjO5OmiI; arc=none smtp.client-ip=209.85.166.42 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="fjO5OmiI" Received: by mail-io1-f42.google.com with SMTP id ca18e2360f4ac-83ac817aac3so224087339f.0 for ; Tue, 29 Oct 2024 08:23:09 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215388; x=1730820188; darn=vger.kernel.org; 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=1wzBUpdtpa3hgDqW+hLOo7TP8QbExzAyYMIVCGHCt2s=; b=fjO5OmiInsLraK6U0/nHbSqHpvoHB6WskVFk7bhJUBBA0H/SX8m9QgNSsy1rr2VO1u wFHozHsmy1GJaDCELIMzPIQhYgir/3c+ls+wrCjYiXRgJCY+SQnM6O9jmardcPz7v+Zb C/TgFkqLmM30EQiG61+Jchc3UY91okorZgJ7MM+2S8ixRDxJL6+28RbxDUyV/R8DxXpt MYiXCHt/FKw+d/O6aGqvna4rqSzY8X4BVcfInMcuiUJlrSn8Vsjm0Ov9rtKsxpkZrV/F iF3jJynflcgEd46dSA9AFSet844fRjYOeNnfufsIgvQqGUa5OgxgdiMPbM+VJqle0n6q y3Xw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215388; x=1730820188; 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=1wzBUpdtpa3hgDqW+hLOo7TP8QbExzAyYMIVCGHCt2s=; b=Fvc/srURxK06ch3ykORWFajx+LzP06il4qqVbBHcZfiuodAAOAsesRy9Q5sXed3fft EjenACWFn/fn0QGL7jDNvuA3pSrbXYeStqs8zdQz3bdsNuIrY/kNN/n9QP7VNNIOMhV8 Gm5KS64n2H+DHHwRaJlRzvssQ3KLFUFmLBGQHeHdBwNK4rnpIBXPSLs2Wg8NwKQXBBjM TNOYPR9dBfTNfuQijpw83UM8Psl5A3Mi1Fx29J3WA43y0sJuUs9yuMAw690Apk9GBxXD Uwyc8yLWlJr3w7kuHaM0ED60j4dyUA5ciC7ToD/7eZEeDNmRJ9yI4ZUmDPqNxFphpZHK FRjw== X-Gm-Message-State: AOJu0Yw784MCOHOGA0mOcWoiExKyG8Yq+oma47W9kJz1TJZ523Lm6rPh e6WDi57IKqkxJ/Jtj05lgiRgNrVtcuFZQI8USEm0rQHTSfRlkYaS+Xz7PE1kdVpeoUIE8ol46sQ W X-Google-Smtp-Source: AGHT+IFLeKfustyDdRJxQJ7GI181AUb8Du1hiK6ihHsBFuXyAp3j/8yl1Y5CZ12lejKPHY8IVouQzw== X-Received: by 2002:a05:6602:160f:b0:82d:16fa:52dd with SMTP id ca18e2360f4ac-83b5670c468mr13553339f.7.1730215387960; Tue, 29 Oct 2024 08:23:07 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.06 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:06 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 04/14] io_uring/splice: open code 2nd direct file assignment Date: Tue, 29 Oct 2024 09:16:33 -0600 Message-ID: <20241029152249.667290-5-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 In preparation for not pinning the whole registered file table, open code the second potential direct file assignment. This will be handled by appropriate helpers in the future, for now just do it manually. Signed-off-by: Jens Axboe --- io_uring/opdef.c | 2 ++ io_uring/splice.c | 44 ++++++++++++++++++++++++++++++++++++-------- io_uring/splice.h | 1 + 3 files changed, 39 insertions(+), 8 deletions(-) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index a2be3bbca5ff..3de75eca1c92 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -641,6 +641,7 @@ const struct io_cold_def io_cold_defs[] = { }, [IORING_OP_SPLICE] = { .name = "SPLICE", + .cleanup = io_splice_cleanup, }, [IORING_OP_PROVIDE_BUFFERS] = { .name = "PROVIDE_BUFFERS", @@ -650,6 +651,7 @@ const struct io_cold_def io_cold_defs[] = { }, [IORING_OP_TEE] = { .name = "TEE", + .cleanup = io_splice_cleanup, }, [IORING_OP_SHUTDOWN] = { .name = "SHUTDOWN", diff --git a/io_uring/splice.c b/io_uring/splice.c index 3b659cd23e9d..e62bc6497a94 100644 --- a/io_uring/splice.c +++ b/io_uring/splice.c @@ -21,6 +21,7 @@ struct io_splice { u64 len; int splice_fd_in; unsigned int flags; + struct io_rsrc_node *rsrc_node; }; static int __io_splice_prep(struct io_kiocb *req, @@ -34,6 +35,7 @@ static int __io_splice_prep(struct io_kiocb *req, if (unlikely(sp->flags & ~valid_flags)) return -EINVAL; sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); + sp->rsrc_node = NULL; req->flags |= REQ_F_FORCE_ASYNC; return 0; } @@ -45,6 +47,38 @@ int io_tee_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return __io_splice_prep(req, sqe); } +void io_splice_cleanup(struct io_kiocb *req) +{ + struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice); + + io_put_rsrc_node(req->ctx, sp->rsrc_node); +} + +static struct file *io_splice_get_file(struct io_kiocb *req, + unsigned int issue_flags) +{ + struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice); + struct io_ring_ctx *ctx = req->ctx; + struct io_fixed_file *slot; + struct file *file = NULL; + + if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) + return io_file_get_normal(req, sp->splice_fd_in); + + io_ring_submit_lock(ctx, issue_flags); + if (unlikely(sp->splice_fd_in >= ctx->nr_user_files)) + goto out; + sp->splice_fd_in = array_index_nospec(sp->splice_fd_in, ctx->nr_user_files); + slot = &ctx->file_table.files[sp->splice_fd_in]; + if (!req->rsrc_node) + __io_req_set_rsrc_node(req, ctx); + file = io_slot_file(slot); + req->flags |= REQ_F_NEED_CLEANUP; +out: + io_ring_submit_unlock(ctx, issue_flags); + return file; +} + int io_tee(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice); @@ -55,10 +89,7 @@ int io_tee(struct io_kiocb *req, unsigned int issue_flags) WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); - if (sp->flags & SPLICE_F_FD_IN_FIXED) - in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); - else - in = io_file_get_normal(req, sp->splice_fd_in); + in = io_splice_get_file(req, issue_flags); if (!in) { ret = -EBADF; goto done; @@ -96,10 +127,7 @@ int io_splice(struct io_kiocb *req, unsigned int issue_flags) WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); - if (sp->flags & SPLICE_F_FD_IN_FIXED) - in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); - else - in = io_file_get_normal(req, sp->splice_fd_in); + in = io_splice_get_file(req, issue_flags); if (!in) { ret = -EBADF; goto done; diff --git a/io_uring/splice.h b/io_uring/splice.h index 542f94168ad3..b9b2848327fb 100644 --- a/io_uring/splice.h +++ b/io_uring/splice.h @@ -3,5 +3,6 @@ int io_tee_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_tee(struct io_kiocb *req, unsigned int issue_flags); +void io_splice_cleanup(struct io_kiocb *req); int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_splice(struct io_kiocb *req, unsigned int issue_flags); From patchwork Tue Oct 29 15:16:34 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855090 Received: from mail-io1-f49.google.com (mail-io1-f49.google.com [209.85.166.49]) (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 8DDB8194C86 for ; Tue, 29 Oct 2024 15:23:10 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.49 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215392; cv=none; b=scidT9Nu4niV8jLOsZyPsFXTwOLJ7UDU2hX3tUxLnW9euU7K0/x7hCWUfMUn53sf6/4mJIbPod5gHO28Jfuk314tYyz3+n1T1B+uA/r5JOX2muvMJ5pYd3IdC/c4mcJ8tgXzOtSpSL7fnnPL8+2xyUxzijrDLa1ri5XJjTzfdpI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215392; c=relaxed/simple; bh=/fVZOAilfDDBwA4j0A3RHIJMhEBKne+Py4wXuj7ry3I=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=JiggElKptD4ERRVv0UGruN1axKFgSqDcIPxFfwneL71kUzyhZ1nmY/JIOkYNqJbKROHm9FI+P2VS9kXe1n4i4fkIp1MV7bGcGoISrEkdawfYNeAGMEIwIN1BQ1XKu/sAZ3BlvT7uuYHa9rvAtalaC+q53WwS+teNkk8H9rlfBHo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=E+hWgWhb; arc=none smtp.client-ip=209.85.166.49 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="E+hWgWhb" Received: by mail-io1-f49.google.com with SMTP id ca18e2360f4ac-83ab694ebe5so212160939f.0 for ; Tue, 29 Oct 2024 08:23:10 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215389; x=1730820189; darn=vger.kernel.org; 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=KdiXgBsgaIl4AHuNvVMJAsYeocIhfg9+qcEY/qVH01A=; b=E+hWgWhbyemzudHxa9xxKnA702wpQxhloO4+8kEn7hq49vZYvVD1u8Tk/Efe28o6nd Y2B7kUdebEZOnq0mK+5TIqL+GZX2GT46AI1azxuN31ohENDP6F9NuOSeb31xa9adwCJH TQexYejIBQr0OzdPGX/6t9we+BdRFyvb3EzzTty/p/RYK5VTmkDJJM9CR/EeMb4TFt+D N/L3DE7JibBZFQplKdrXWhEN9b8tqE2rHbrYor/WAfKweeqky+hcePKtc0AyYSQEdGgX +mfXu8KyLNYrAanKT1EkVR3o0mq6PXefPF1VY/wtwCkqXhCowvQSuismcNi1WBQ9VVY1 Hs+Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215389; x=1730820189; 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=KdiXgBsgaIl4AHuNvVMJAsYeocIhfg9+qcEY/qVH01A=; b=J6AJRDKNHuqE193t28iJu1yt/fqLMZz6aH8l0dvLJUdsAseX4dpeZw8C6858I+vE6n TE7U+plPbwOfksGW/NMX4sYeftx76Hl0jTBoZ4I5HOzdaSeNgRbjheTI6y4hS59Gy92S wi4MiocpBQOC1YxldW9pSBRqfM6w8K0IhFZEEio6//rzAcdKb7822XQhYSjN0a89kafW ohES9bj/9646pRFxfM8VFbL/uEBvzd9z3x8AvYuwKlQMK1KT+hkfCAFpHFcdOlugdX8T KT2cOA6UFMQpO/L2sQoTkgEUGDSR70ah8E8ILjeI+kpX5rzFEJBnU2nlN61auWNERr93 5+4w== X-Gm-Message-State: AOJu0YzX/e/v/CjJsO3hHozwHc0nepb/JSDUlQaF5YTnG9NWq9U0657X dUJms8GatTfV2I3UGxThlj5p9Pf1Gmwu/HqfnPmVJH4J9Sfep6qs3UFkUlgxzP5MHVwckRheFW8 R X-Google-Smtp-Source: AGHT+IHG6PyuKepxv9mBktGmzcCtLCx8Lj4OfLvqeS4HdlUR0M8yshsCPi9Y6f975JuRcGAcAHtFaA== X-Received: by 2002:a05:6602:1589:b0:837:7d54:acf1 with SMTP id ca18e2360f4ac-83b1c3b7c50mr1150274639f.2.1730215389232; Tue, 29 Oct 2024 08:23:09 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.08 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:08 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 05/14] io_uring/rsrc: kill io_charge_rsrc_node() Date: Tue, 29 Oct 2024 09:16:34 -0600 Message-ID: <20241029152249.667290-6-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 It's only used from __io_req_set_rsrc_node(), and it takes both the ctx and node itself, while never using the ctx. Just open-code the basic refs++ in __io_req_set_rsrc_node() instead. Signed-off-by: Jens Axboe --- io_uring/rsrc.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index e072fb3ee351..1589c9740083 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -97,18 +97,12 @@ static inline void io_put_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node io_rsrc_node_ref_zero(node); } -static inline void io_charge_rsrc_node(struct io_ring_ctx *ctx, - struct io_rsrc_node *node) -{ - node->refs++; -} - static inline void __io_req_set_rsrc_node(struct io_kiocb *req, struct io_ring_ctx *ctx) { lockdep_assert_held(&ctx->uring_lock); req->rsrc_node = ctx->rsrc_node; - io_charge_rsrc_node(ctx, ctx->rsrc_node); + ctx->rsrc_node->refs++; } static inline void io_req_set_rsrc_node(struct io_kiocb *req, From patchwork Tue Oct 29 15:16:35 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855094 Received: from mail-io1-f47.google.com (mail-io1-f47.google.com [209.85.166.47]) (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 4C5EA192D73 for ; Tue, 29 Oct 2024 15:23:12 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.47 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215398; cv=none; b=OJBKDXbjdqjinZWCh0un3grMDknyoXsEr99IWcoC7ipDhmkkCkeTVEuPf38iSsBcFRuvVveAK3hA+McIEz2zy1JGP8zHFOh33n/qC9QO2UxL04NG0pLembZLqCXlhGLHqwlrJRsZ2hsTXauvrUhSotkSAEtCti+xL4kAp9rx6V0= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215398; c=relaxed/simple; bh=rrYc8QxJZjtACr3rDws3gOPUbamqv8LDvlTGAhmYsJM=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=bQDZj3iN5P1ulOERUOB+d6XNJvBc7omKNj+Txmut2uMBcLqhtDEQW4eLp3/kGqLAxuPbpVsJ/OgXC9oKoJX86eEN/a/80DcJsR9zFzOCpYmnn0CFm8MFE3+Y11MIoP+OwlQID0jJIZM1Jbad1d6RxfQyuARFbbaU4/LytvLEl7M= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=1+nEl7tH; arc=none smtp.client-ip=209.85.166.47 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="1+nEl7tH" Received: by mail-io1-f47.google.com with SMTP id ca18e2360f4ac-83ac05206f6so220053039f.2 for ; Tue, 29 Oct 2024 08:23:12 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215391; x=1730820191; darn=vger.kernel.org; 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=zP8PSO9nDyVeha6FI/vDMeHO48afNlfSXRjIEo17AVg=; b=1+nEl7tHuM3K5NHbkOtEZowDLubnfmDnVmgLsnQmgWlID+W9qpdHj20e9deEoXHOzs EJKQ3KVN+pUord4jYWX+RE8EAhE5mZkeWpz5Jv+WnHUji4MGwbMpOPuJ5scL3TBly/Pd HHJLEUWc7hVoJHKPIDdNPzP1FWLy9oFa77IUuHGkHoEj27fKeKkZfNPetzE4akwKK1tv 7KnwnaAFGCB17SoqP52LHu3hZR8ifYBhpvwcvW0yceEsZQmcsJpN2wNAPn7A6DCcymQ1 9RaBbvVczTvPYPZrtvvIkv/pi0o5XqymDs00wMfWNEh+giYMUl4VsZliYGsoVzC21ELj hwgg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215391; x=1730820191; 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=zP8PSO9nDyVeha6FI/vDMeHO48afNlfSXRjIEo17AVg=; b=iYDk4SOWJeqlwPz+o30DuupHvTIF7XBTl7+5o7LEuOKoT1loeTIEo2W3IEeqMlqlvN 5kd5zJ/0+hZ9i3EVV18lqDmcURqk91BRBwWuqsI7v0c+u0o3Lg3f4Gtdprr5DlgP/pay +9A63Q1SObsv8i5KTTA/Og4rxY7sk49vMAmE5JcLstyoddLQyJhrcqsXiC1gbsLTzESL +C85i1cL05XVLt7/ExezEDl3+nDUJ6eWfYO6B9wJ7y7lAAKF6znsC0xy1s7k7vBcgWBK 3cG0A3qpvU6jSg+kLMADR3aN2DAP/0bUEiDHJ+Vb9xi3Pw8duKg7+1qCuTyN1Ju5VJeq tfXg== X-Gm-Message-State: AOJu0YyBwrR95znuR76erJPbVtuYZaOu6T9uPA/sAoWKKk9/U7yooSYi jBdJKIVD11XBpYvONg0ZWw+Sx1yVa70yqrcK6avwC8MBinteRubQV1f0ozd/Meo5IMeS8ucZ0Pg h X-Google-Smtp-Source: AGHT+IGVLFwpQie4rZ5VXIXhUFNRIi2k/w/H9ra4ToQljl+/Lyv3Achw7epttx2Gh33Zw/Z5mWYnSQ== X-Received: by 2002:a05:6602:1402:b0:837:6dae:207b with SMTP id ca18e2360f4ac-83b1c5fa56fmr1220330839f.16.1730215390574; Tue, 29 Oct 2024 08:23:10 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.09 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:09 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 06/14] io_uring/rsrc: get rid of per-ring io_rsrc_node list Date: Tue, 29 Oct 2024 09:16:35 -0600 Message-ID: <20241029152249.667290-7-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Work in progress, but get rid of the per-ring serialization of resource nodes, like registered buffers and files. Main issue here is that one node can otherwise hold up a bunch of other nodes from getting freed, which is especially a problem for file resource nodes and networked workloads where some descriptors may not see activity in a long time. As an example, instantiate an io_uring ring fd and create a sparse registered file table. Even 2 will do. Then create a socket and register it as fixed file 0, F0. The number of open files in the app is now 5, with 0/1/2 being the usual stdin/out/err, 3 being the ring fd, and 4 being the socket. Register this socket (eg "the listener") in slot 0 of the registered file table. Now add an operation on the socket that uses slot 0. Finally, loop N times, where each loop creates a new socket, registers said socket as a file, then unregisters the socket, and finally closes the socket. This is roughly similar to what a basic accept loop would look like. At the end of this loop, it's not unreasonable to expect that there would still be 5 open files. Each socket created and registered in the loop is also unregistered and closed. But since the listener socket registered first still has references to its resource node due to still being active, each subsequent socket unregistration is stuck behind it for reclaim. Hence 5 + N files are still open at that point, where N is awaiting the final put held up by the listener socket. Rewrite the io_rsrc_node handling to NOT rely on serialization. Struct io_kiocb now gets explicit resource nodes assigned, with each holding a reference to the parent node. A parent node is either of type FILE or BUFFER, which are the two types of nodes that exist. A request can have two nodes assigned, if it's using both registered files and buffers. Since request issue and task_work completion is both under the ring private lock, no atomics are needed to handle these references. It's a simple unlocked inc/dec. As before, the registered buffer or file table each hold a reference as well to the registered nodes. Final put of the node will remove the node and free the underlying resource, eg unmap the buffer or put the file. Outside of removing the stall in resource reclaim described above, it has the following advantages: 1) It's a lot simpler than the previous scheme, and easier to follow. No need to specific quiesce handling anymore. 2) There are no resource node allocations in the fast path, all of that happens at resource registration time. 3) The structs related to resource handling can all get simplified quite a bit, like io_rsrc_node and io_rsrc_data. io_rsrc_put can go away completely. 4) Handling of resource tags is much simpler, and doesn't require persistent storage as it can simply get assigned up front at registration time. Just copy them in one-by-one at registration time and assign to the resource node. The only real downside is that a request is now explicitly limited to pinning 2 resources, one file and one buffer, where before just assigning a resource node to a request would pin all of them. The upside is that it's easier to follow now, as an individual resource is explicitly referenced and assigned to the request. With this in place, the above mentioned example will be using exactly 5 files at the end of the loop, not N. Needs to get broken up a bit and there are certainly rough edges, but that's why it's a work in progress... But it does remove a ton more code than it adds, and passes the liburing tests. Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 10 +- io_uring/fdinfo.c | 2 +- io_uring/filetable.c | 52 ++-- io_uring/filetable.h | 25 +- io_uring/io_uring.c | 38 +-- io_uring/net.c | 11 +- io_uring/nop.c | 6 +- io_uring/notif.c | 3 +- io_uring/rsrc.c | 482 ++++++++++++--------------------- io_uring/rsrc.h | 72 ++--- io_uring/rw.c | 8 +- io_uring/splice.c | 16 +- io_uring/uring_cmd.c | 12 +- 13 files changed, 272 insertions(+), 465 deletions(-) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index d4ba4ae480d6..42c5f2c992c4 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -56,7 +56,7 @@ struct io_wq_work { }; struct io_file_table { - struct io_fixed_file *files; + struct io_rsrc_node **nodes; unsigned long *bitmap; unsigned int alloc_hint; }; @@ -264,7 +264,6 @@ struct io_ring_ctx { * Fixed resources fast path, should be accessed only under * uring_lock, and updated through io_uring_register(2) */ - struct io_rsrc_node *rsrc_node; atomic_t cancel_seq; /* @@ -277,7 +276,7 @@ struct io_ring_ctx { struct io_wq_work_list iopoll_list; struct io_file_table file_table; - struct io_mapped_ubuf **user_bufs; + struct io_rsrc_node **user_bufs; unsigned nr_user_files; unsigned nr_user_bufs; @@ -372,10 +371,7 @@ struct io_ring_ctx { struct io_rsrc_data *buf_data; /* protected by ->uring_lock */ - struct list_head rsrc_ref_list; struct io_alloc_cache rsrc_node_cache; - struct wait_queue_head rsrc_quiesce_wq; - unsigned rsrc_quiesce; u32 pers_next; struct xarray personalities; @@ -642,7 +638,7 @@ struct io_kiocb { __poll_t apoll_events; }; - struct io_rsrc_node *rsrc_node; + struct io_rsrc_node *rsrc_nodes[2]; atomic_t refs; bool cancel_seq_set; diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index a6bac533edbe..064a79475c5f 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -176,7 +176,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) } seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) { - struct io_mapped_ubuf *buf = ctx->user_bufs[i]; + struct io_mapped_ubuf *buf = ctx->user_bufs[i]->buf; seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, buf->len); } diff --git a/io_uring/filetable.c b/io_uring/filetable.c index 997c56d32ee6..a01be324ac15 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -38,14 +38,14 @@ static int io_file_bitmap_get(struct io_ring_ctx *ctx) bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) { - table->files = kvcalloc(nr_files, sizeof(table->files[0]), - GFP_KERNEL_ACCOUNT); - if (unlikely(!table->files)) + table->nodes = kvmalloc_array(nr_files, sizeof(struct io_src_node *), + GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (unlikely(!table->nodes)) return false; table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT); if (unlikely(!table->bitmap)) { - kvfree(table->files); + kvfree(table->nodes); return false; } @@ -54,9 +54,9 @@ bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) void io_free_file_tables(struct io_file_table *table) { - kvfree(table->files); + kvfree(table->nodes); bitmap_free(table->bitmap); - table->files = NULL; + table->nodes = NULL; table->bitmap = NULL; } @@ -64,8 +64,7 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, u32 slot_index) __must_hold(&req->ctx->uring_lock) { - struct io_fixed_file *file_slot; - int ret; + struct io_rsrc_node *node; if (io_is_uring_fops(file)) return -EBADF; @@ -74,22 +73,18 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, if (slot_index >= ctx->nr_user_files) return -EINVAL; - slot_index = array_index_nospec(slot_index, ctx->nr_user_files); - file_slot = io_fixed_file_slot(&ctx->file_table, slot_index); - - if (file_slot->file_ptr) { - ret = io_queue_rsrc_removal(ctx->file_data, slot_index, - io_slot_file(file_slot)); - if (ret) - return ret; + node = io_rsrc_node_alloc(ctx, ctx->file_data, IORING_RSRC_FILE); + if (IS_ERR(node)) + return -ENOMEM; - file_slot->file_ptr = 0; - } else { + slot_index = array_index_nospec(slot_index, ctx->nr_user_files); + if (ctx->file_table.nodes[slot_index]) + io_put_rsrc_node(ctx->file_table.nodes[slot_index]); + else io_file_bitmap_set(&ctx->file_table, slot_index); - } - *io_get_tag_slot(ctx->file_data, slot_index) = 0; - io_fixed_file_set(file_slot, file); + ctx->file_table.nodes[slot_index] = node; + io_fixed_file_set(node, file); return 0; } @@ -134,25 +129,16 @@ int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags, int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset) { - struct io_fixed_file *file_slot; - int ret; - if (unlikely(!ctx->file_data)) return -ENXIO; if (offset >= ctx->nr_user_files) return -EINVAL; offset = array_index_nospec(offset, ctx->nr_user_files); - file_slot = io_fixed_file_slot(&ctx->file_table, offset); - if (!file_slot->file_ptr) + if (!ctx->file_table.nodes[offset]) return -EBADF; - - ret = io_queue_rsrc_removal(ctx->file_data, offset, - io_slot_file(file_slot)); - if (ret) - return ret; - - file_slot->file_ptr = 0; + io_put_rsrc_node(ctx->file_table.nodes[offset]); + ctx->file_table.nodes[offset] = NULL; io_file_bitmap_clear(&ctx->file_table, offset); return 0; } diff --git a/io_uring/filetable.h b/io_uring/filetable.h index c027ed4ad68d..47616079abaa 100644 --- a/io_uring/filetable.h +++ b/io_uring/filetable.h @@ -34,36 +34,35 @@ static inline void io_file_bitmap_set(struct io_file_table *table, int bit) table->alloc_hint = bit + 1; } -static inline struct io_fixed_file * -io_fixed_file_slot(struct io_file_table *table, unsigned i) -{ - return &table->files[i]; -} - #define FFS_NOWAIT 0x1UL #define FFS_ISREG 0x2UL #define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG) -static inline unsigned int io_slot_flags(struct io_fixed_file *slot) +static inline unsigned int io_slot_flags(struct io_rsrc_node *node) { - return (slot->file_ptr & ~FFS_MASK) << REQ_F_SUPPORT_NOWAIT_BIT; + + return (node->file_ptr & ~FFS_MASK) << REQ_F_SUPPORT_NOWAIT_BIT; } -static inline struct file *io_slot_file(struct io_fixed_file *slot) +static inline struct file *io_slot_file(struct io_rsrc_node *node) { - return (struct file *)(slot->file_ptr & FFS_MASK); + return (struct file *)(node->file_ptr & FFS_MASK); } static inline struct file *io_file_from_index(struct io_file_table *table, int index) { - return io_slot_file(io_fixed_file_slot(table, index)); + struct io_rsrc_node *node = table->nodes[index]; + + if (node) + return io_slot_file(node); + return NULL; } -static inline void io_fixed_file_set(struct io_fixed_file *file_slot, +static inline void io_fixed_file_set(struct io_rsrc_node *node, struct file *file) { - file_slot->file_ptr = (unsigned long)file | + node->file_ptr = (unsigned long)file | (io_file_get_flags(file) >> REQ_F_SUPPORT_NOWAIT_BIT); } diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index a09c67b38c1b..0876aa74c739 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -333,7 +333,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) mutex_init(&ctx->uring_lock); init_waitqueue_head(&ctx->cq_wait); init_waitqueue_head(&ctx->poll_wq); - init_waitqueue_head(&ctx->rsrc_quiesce_wq); spin_lock_init(&ctx->completion_lock); spin_lock_init(&ctx->timeout_lock); INIT_WQ_LIST(&ctx->iopoll_list); @@ -341,7 +340,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->defer_list); INIT_LIST_HEAD(&ctx->timeout_list); INIT_LIST_HEAD(&ctx->ltimeout_list); - INIT_LIST_HEAD(&ctx->rsrc_ref_list); init_llist_head(&ctx->work_llist); INIT_LIST_HEAD(&ctx->tctx_list); ctx->submit_state.free_list.next = NULL; @@ -1415,7 +1413,7 @@ static void io_free_batch_list(struct io_ring_ctx *ctx, io_clean_op(req); } io_put_file(req); - io_put_rsrc_node(ctx, req->rsrc_node); + io_req_put_rsrc_nodes(req); io_put_task(req->task); node = req->comp_list.next; @@ -1878,7 +1876,7 @@ inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; - struct io_fixed_file *slot; + struct io_rsrc_node *node; struct file *file = NULL; io_ring_submit_lock(ctx, issue_flags); @@ -1886,11 +1884,12 @@ inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, if (unlikely((unsigned int)fd >= ctx->nr_user_files)) goto out; fd = array_index_nospec(fd, ctx->nr_user_files); - slot = io_fixed_file_slot(&ctx->file_table, fd); - if (!req->rsrc_node) - __io_req_set_rsrc_node(req, ctx); - req->flags |= io_slot_flags(slot); - file = io_slot_file(slot); + node = ctx->file_table.nodes[fd]; + if (node) { + io_req_assign_rsrc_node(req, node); + req->flags |= io_slot_flags(node); + file = io_slot_file(node); + } out: io_ring_submit_unlock(ctx, issue_flags); return file; @@ -2036,7 +2035,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->flags = (__force io_req_flags_t) sqe_flags; req->cqe.user_data = READ_ONCE(sqe->user_data); req->file = NULL; - req->rsrc_node = NULL; + req->rsrc_nodes[IORING_RSRC_FILE] = NULL; + req->rsrc_nodes[IORING_RSRC_BUFFER] = NULL; req->task = current; req->cancel_seq_set = false; @@ -2718,15 +2718,10 @@ static void io_req_caches_free(struct io_ring_ctx *ctx) static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) { io_sq_thread_finish(ctx); - /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ - if (WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list))) - return; mutex_lock(&ctx->uring_lock); - if (ctx->buf_data) - __io_sqe_buffers_unregister(ctx); - if (ctx->file_data) - __io_sqe_files_unregister(ctx); + io_sqe_buffers_unregister(ctx); + io_sqe_files_unregister(ctx); io_cqring_overflow_kill(ctx); io_eventfd_unregister(ctx); io_alloc_cache_free(&ctx->apoll_cache, kfree); @@ -2743,11 +2738,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) if (ctx->submitter_task) put_task_struct(ctx->submitter_task); - /* there are no registered resources left, nobody uses it */ - if (ctx->rsrc_node) - io_rsrc_node_destroy(ctx, ctx->rsrc_node); - - WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)); WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); io_alloc_cache_free(&ctx->rsrc_node_cache, kfree); @@ -3729,10 +3719,6 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, if (ret) goto err; - ret = io_rsrc_init(ctx); - if (ret) - goto err; - p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | diff --git a/io_uring/net.c b/io_uring/net.c index 2040195e33ab..ce1156551d10 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1342,15 +1342,15 @@ static int io_send_zc_import(struct io_kiocb *req, unsigned int issue_flags) if (sr->flags & IORING_RECVSEND_FIXED_BUF) { struct io_ring_ctx *ctx = req->ctx; - struct io_mapped_ubuf *imu; + struct io_rsrc_node *node; int idx; ret = -EFAULT; io_ring_submit_lock(ctx, issue_flags); if (sr->buf_index < ctx->nr_user_bufs) { idx = array_index_nospec(sr->buf_index, ctx->nr_user_bufs); - imu = READ_ONCE(ctx->user_bufs[idx]); - io_req_set_rsrc_node(sr->notif, ctx); + node = ctx->user_bufs[idx]; + io_req_assign_rsrc_node(sr->notif, node); ret = 0; } io_ring_submit_unlock(ctx, issue_flags); @@ -1358,8 +1358,9 @@ static int io_send_zc_import(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(ret)) return ret; - ret = io_import_fixed(ITER_SOURCE, &kmsg->msg.msg_iter, imu, - (u64)(uintptr_t)sr->buf, sr->len); + ret = io_import_fixed(ITER_SOURCE, &kmsg->msg.msg_iter, + node->buf, (u64)(uintptr_t)sr->buf, + sr->len); if (unlikely(ret)) return ret; kmsg->msg.sg_from_iter = io_sg_from_iter; diff --git a/io_uring/nop.c b/io_uring/nop.c index 2c7a22ba4053..de91600a3bc6 100644 --- a/io_uring/nop.c +++ b/io_uring/nop.c @@ -61,15 +61,15 @@ int io_nop(struct io_kiocb *req, unsigned int issue_flags) } if (nop->flags & IORING_NOP_FIXED_BUFFER) { struct io_ring_ctx *ctx = req->ctx; - struct io_mapped_ubuf *imu; + struct io_rsrc_node *node; int idx; ret = -EFAULT; io_ring_submit_lock(ctx, issue_flags); if (nop->buffer < ctx->nr_user_bufs) { idx = array_index_nospec(nop->buffer, ctx->nr_user_bufs); - imu = READ_ONCE(ctx->user_bufs[idx]); - io_req_set_rsrc_node(req, ctx); + node = READ_ONCE(ctx->user_bufs[idx]); + io_req_assign_rsrc_node(req, node); ret = 0; } io_ring_submit_unlock(ctx, issue_flags); diff --git a/io_uring/notif.c b/io_uring/notif.c index 28859ae3ee6e..4f02e969cf08 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -117,7 +117,8 @@ struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx) notif->file = NULL; notif->task = current; io_get_task_refs(1); - notif->rsrc_node = NULL; + notif->rsrc_nodes[IORING_RSRC_FILE] = NULL; + notif->rsrc_nodes[IORING_RSRC_BUFFER] = NULL; nd = io_notif_to_data(notif); nd->zc_report = false; diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index ca2ec8a018be..e32c4d1bef86 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -26,10 +26,8 @@ struct io_rsrc_update { u32 offset; }; -static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc); -static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, - struct io_mapped_ubuf **pimu, - struct page **last_hpage); +static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, + struct iovec *iov, int index, struct page **last_hpage); /* only define max */ #define IORING_MAX_FIXED_FILES (1U << 20) @@ -110,13 +108,13 @@ static int io_buffer_validate(struct iovec *iov) return 0; } -static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slot) +static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_rsrc_node *node) { - struct io_mapped_ubuf *imu = *slot; unsigned int i; - *slot = NULL; - if (imu != &dummy_ubuf) { + if (node->buf != &dummy_ubuf) { + struct io_mapped_ubuf *imu = node->buf; + if (!refcount_dec_and_test(&imu->refs)) return; for (i = 0; i < imu->nr_bvecs; i++) @@ -127,205 +125,56 @@ static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slo } } -static void io_rsrc_put_work(struct io_rsrc_node *node) +struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, + struct io_rsrc_data *data, int type) { - struct io_rsrc_put *prsrc = &node->item; - - if (prsrc->tag) - io_post_aux_cqe(node->ctx, prsrc->tag, 0, 0); - - switch (node->type) { - case IORING_RSRC_FILE: - fput(prsrc->file); - break; - case IORING_RSRC_BUFFER: - io_rsrc_buf_put(node->ctx, prsrc); - break; - default: - WARN_ON_ONCE(1); - break; - } -} - -void io_rsrc_node_destroy(struct io_ring_ctx *ctx, struct io_rsrc_node *node) -{ - if (!io_alloc_cache_put(&ctx->rsrc_node_cache, node)) - kfree(node); -} - -void io_rsrc_node_ref_zero(struct io_rsrc_node *node) - __must_hold(&node->ctx->uring_lock) -{ - struct io_ring_ctx *ctx = node->ctx; + struct io_rsrc_node *node; - while (!list_empty(&ctx->rsrc_ref_list)) { - node = list_first_entry(&ctx->rsrc_ref_list, - struct io_rsrc_node, node); - /* recycle ref nodes in order */ - if (node->refs) - break; - list_del(&node->node); - - if (likely(!node->empty)) - io_rsrc_put_work(node); - io_rsrc_node_destroy(ctx, node); - } - if (list_empty(&ctx->rsrc_ref_list) && unlikely(ctx->rsrc_quiesce)) - wake_up_all(&ctx->rsrc_quiesce_wq); -} - -struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx) -{ - struct io_rsrc_node *ref_node; - - ref_node = io_alloc_cache_get(&ctx->rsrc_node_cache); - if (!ref_node) { - ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); - if (!ref_node) + node = io_alloc_cache_get(&ctx->rsrc_node_cache); + if (!node) { + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) return NULL; } - ref_node->ctx = ctx; - ref_node->empty = 0; - ref_node->refs = 1; - return ref_node; -} - -__cold static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, - struct io_ring_ctx *ctx) -{ - struct io_rsrc_node *backup; - DEFINE_WAIT(we); - int ret; - - /* As We may drop ->uring_lock, other task may have started quiesce */ - if (data->quiesce) - return -ENXIO; - - backup = io_rsrc_node_alloc(ctx); - if (!backup) - return -ENOMEM; - ctx->rsrc_node->empty = true; - ctx->rsrc_node->type = -1; - list_add_tail(&ctx->rsrc_node->node, &ctx->rsrc_ref_list); - io_put_rsrc_node(ctx, ctx->rsrc_node); - ctx->rsrc_node = backup; - - if (list_empty(&ctx->rsrc_ref_list)) - return 0; - - if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) { - atomic_set(&ctx->cq_wait_nr, 1); - smp_mb(); - } - - ctx->rsrc_quiesce++; - data->quiesce = true; - do { - prepare_to_wait(&ctx->rsrc_quiesce_wq, &we, TASK_INTERRUPTIBLE); - mutex_unlock(&ctx->uring_lock); - - ret = io_run_task_work_sig(ctx); - if (ret < 0) { - finish_wait(&ctx->rsrc_quiesce_wq, &we); - mutex_lock(&ctx->uring_lock); - if (list_empty(&ctx->rsrc_ref_list)) - ret = 0; - break; - } - - schedule(); - mutex_lock(&ctx->uring_lock); - ret = 0; - } while (!list_empty(&ctx->rsrc_ref_list)); - - finish_wait(&ctx->rsrc_quiesce_wq, &we); - data->quiesce = false; - ctx->rsrc_quiesce--; - - if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) { - atomic_set(&ctx->cq_wait_nr, 0); - smp_mb(); - } - return ret; -} - -static void io_free_page_table(void **table, size_t size) -{ - unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); - - for (i = 0; i < nr_tables; i++) - kfree(table[i]); - kfree(table); + node->ctx = ctx; + node->refs = 1; + node->type = type; + return node; } static void io_rsrc_data_free(struct io_rsrc_data *data) { - size_t size = data->nr * sizeof(data->tags[0][0]); - - if (data->tags) - io_free_page_table((void **)data->tags, size); - kfree(data); -} - -static __cold void **io_alloc_page_table(size_t size) -{ - unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); - size_t init_size = size; - void **table; - - table = kcalloc(nr_tables, sizeof(*table), GFP_KERNEL_ACCOUNT); - if (!table) - return NULL; + int i; - for (i = 0; i < nr_tables; i++) { - unsigned int this_size = min_t(size_t, size, PAGE_SIZE); + for (i = 0; i < data->nr; i++) { + struct io_rsrc_node *node = data->nodes[i]; - table[i] = kzalloc(this_size, GFP_KERNEL_ACCOUNT); - if (!table[i]) { - io_free_page_table(table, init_size); - return NULL; - } - size -= this_size; + io_put_rsrc_node(node); } - return table; + kvfree(data->nodes); + kfree(data); } -__cold static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, int type, - u64 __user *utags, - unsigned nr, struct io_rsrc_data **pdata) +__cold static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, unsigned nr, + struct io_rsrc_data **pdata) { struct io_rsrc_data *data; - int ret = 0; - unsigned i; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; - data->tags = (u64 **)io_alloc_page_table(nr * sizeof(data->tags[0][0])); - if (!data->tags) { + + data->nodes = kvmalloc_array(nr, sizeof(struct io_rsrc_node *), + GFP_KERNEL | __GFP_ZERO); + if (!data->nodes) { kfree(data); return -ENOMEM; } data->nr = nr; - data->ctx = ctx; - data->rsrc_type = type; - if (utags) { - ret = -EFAULT; - for (i = 0; i < nr; i++) { - u64 *tag_slot = io_get_tag_slot(data, i); - - if (copy_from_user(tag_slot, &utags[i], - sizeof(*tag_slot))) - goto fail; - } - } *pdata = data; return 0; -fail: - io_rsrc_data_free(data); - return ret; } static int __io_sqe_files_update(struct io_ring_ctx *ctx, @@ -334,8 +183,6 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, { u64 __user *tags = u64_to_user_ptr(up->tags); __s32 __user *fds = u64_to_user_ptr(up->data); - struct io_rsrc_data *data = ctx->file_data; - struct io_fixed_file *file_slot; int fd, i, err = 0; unsigned int done; @@ -360,18 +207,14 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, continue; i = array_index_nospec(up->offset + done, ctx->nr_user_files); - file_slot = io_fixed_file_slot(&ctx->file_table, i); - - if (file_slot->file_ptr) { - err = io_queue_rsrc_removal(data, i, - io_slot_file(file_slot)); - if (err) - break; - file_slot->file_ptr = 0; + if (ctx->file_table.nodes[i]) { + io_put_rsrc_node(ctx->file_table.nodes[i]); + ctx->file_table.nodes[i] = NULL; io_file_bitmap_clear(&ctx->file_table, i); } if (fd != -1) { struct file *file = fget(fd); + struct io_rsrc_node *node; if (!file) { err = -EBADF; @@ -385,8 +228,15 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - *io_get_tag_slot(data, i) = tag; - io_fixed_file_set(file_slot, file); + node = io_rsrc_node_alloc(ctx, ctx->file_data, IORING_RSRC_FILE); + if (!node) { + err = -ENOMEM; + fput(file); + break; + } + ctx->file_table.nodes[i] = node; + node->tag = tag; + io_fixed_file_set(node, file); io_file_bitmap_set(&ctx->file_table, i); } } @@ -411,7 +261,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, return -EINVAL; for (done = 0; done < nr_args; done++) { - struct io_mapped_ubuf *imu; + struct io_rsrc_node *node; u64 tag = 0; uvec = u64_to_user_ptr(user_data); @@ -431,23 +281,16 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, err = -EINVAL; break; } - err = io_sqe_buffer_register(ctx, iov, &imu, &last_hpage); - if (err) - break; - i = array_index_nospec(up->offset + done, ctx->nr_user_bufs); - if (ctx->user_bufs[i] != &dummy_ubuf) { - err = io_queue_rsrc_removal(ctx->buf_data, i, - ctx->user_bufs[i]); - if (unlikely(err)) { - io_buffer_unmap(ctx, &imu); - break; - } - ctx->user_bufs[i] = (struct io_mapped_ubuf *)&dummy_ubuf; + node = io_sqe_buffer_register(ctx, iov, i, &last_hpage); + if (IS_ERR(node)) { + err = PTR_ERR(node); + break; } + io_put_rsrc_node(ctx->user_bufs[i]); - ctx->user_bufs[i] = imu; - *io_get_tag_slot(ctx->buf_data, i) = tag; + ctx->user_bufs[i] = node; + node->tag = tag; if (ctx->compat) user_data += sizeof(struct compat_iovec); else @@ -622,38 +465,47 @@ int io_files_update(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } -int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, void *rsrc) +void io_free_rsrc_node(struct io_rsrc_node *node) { - struct io_ring_ctx *ctx = data->ctx; - struct io_rsrc_node *node = ctx->rsrc_node; - u64 *tag_slot = io_get_tag_slot(data, idx); + struct io_ring_ctx *ctx = node->ctx; - ctx->rsrc_node = io_rsrc_node_alloc(ctx); - if (unlikely(!ctx->rsrc_node)) { - ctx->rsrc_node = node; - return -ENOMEM; + lockdep_assert_held(&ctx->uring_lock); + + if (node->tag) + io_post_aux_cqe(node->ctx, node->tag, 0, 0); + + switch (node->type) { + case IORING_RSRC_FILE: + if (io_slot_file(node)) + fput(io_slot_file(node)); + break; + case IORING_RSRC_BUFFER: + if (node->buf) + io_buffer_unmap(node->ctx, node); + break; + default: + WARN_ON_ONCE(1); + break; } - node->item.rsrc = rsrc; - node->type = data->rsrc_type; - node->item.tag = *tag_slot; - *tag_slot = 0; - list_add_tail(&node->node, &ctx->rsrc_ref_list); - io_put_rsrc_node(ctx, node); - return 0; + if (!io_alloc_cache_put(&ctx->rsrc_node_cache, node)) + kfree(node); } -void __io_sqe_files_unregister(struct io_ring_ctx *ctx) +static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) { int i; + lockdep_assert_held(&ctx->uring_lock); + for (i = 0; i < ctx->nr_user_files; i++) { - struct file *file = io_file_from_index(&ctx->file_table, i); + struct io_rsrc_node *node = ctx->file_table.nodes[i]; - if (!file) - continue; - io_file_bitmap_clear(&ctx->file_table, i); - fput(file); + if (node) { + io_put_rsrc_node(node); + io_file_bitmap_clear(&ctx->file_table, i); + ctx->file_table.nodes[i] = NULL; + } } io_free_file_tables(&ctx->file_table); @@ -665,22 +517,11 @@ void __io_sqe_files_unregister(struct io_ring_ctx *ctx) int io_sqe_files_unregister(struct io_ring_ctx *ctx) { - unsigned nr = ctx->nr_user_files; - int ret; - if (!ctx->file_data) return -ENXIO; - /* - * Quiesce may unlock ->uring_lock, and while it's not held - * prevent new requests using the table. - */ - ctx->nr_user_files = 0; - ret = io_rsrc_ref_quiesce(ctx->file_data, ctx); - ctx->nr_user_files = nr; - if (!ret) - __io_sqe_files_unregister(ctx); - return ret; + __io_sqe_files_unregister(ctx); + return 0; } int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, @@ -699,8 +540,7 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return -EMFILE; if (nr_args > rlimit(RLIMIT_NOFILE)) return -EMFILE; - ret = io_rsrc_data_alloc(ctx, IORING_RSRC_FILE, tags, nr_args, - &ctx->file_data); + ret = io_rsrc_data_alloc(ctx, nr_args, &ctx->file_data); if (ret) return ret; @@ -711,16 +551,18 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, } for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { - struct io_fixed_file *file_slot; + struct io_rsrc_node *node; + u64 tag = 0; - if (fds && copy_from_user(&fd, &fds[i], sizeof(fd))) { - ret = -EFAULT; + ret = -EFAULT; + if (tags && copy_from_user(&tag, &tags[i], sizeof(tag))) + goto fail; + if (fds && copy_from_user(&fd, &fds[i], sizeof(fd))) goto fail; - } /* allow sparse sets */ if (!fds || fd == -1) { ret = -EINVAL; - if (unlikely(*io_get_tag_slot(ctx->file_data, i))) + if (tag) goto fail; continue; } @@ -737,8 +579,16 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, fput(file); goto fail; } - file_slot = io_fixed_file_slot(&ctx->file_table, i); - io_fixed_file_set(file_slot, file); + ret = -ENOMEM; + node = io_rsrc_node_alloc(ctx, ctx->file_data, IORING_RSRC_FILE); + if (!node) { + fput(file); + goto fail; + } + if (tag) + node->tag = tag; + ctx->file_table.nodes[i] = node; + io_fixed_file_set(node, file); io_file_bitmap_set(&ctx->file_table, i); } @@ -750,43 +600,30 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return ret; } -static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) -{ - io_buffer_unmap(ctx, &prsrc->buf); - prsrc->buf = NULL; -} - -void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx) +static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx) { unsigned int i; - for (i = 0; i < ctx->nr_user_bufs; i++) - io_buffer_unmap(ctx, &ctx->user_bufs[i]); - kfree(ctx->user_bufs); - io_rsrc_data_free(ctx->buf_data); + lockdep_assert_held(&ctx->uring_lock); + + for (i = 0; i < ctx->nr_user_bufs; i++) { + io_put_rsrc_node(ctx->user_bufs[i]); + ctx->user_bufs[i] = NULL; + } + kvfree(ctx->user_bufs); ctx->user_bufs = NULL; + io_rsrc_data_free(ctx->buf_data); ctx->buf_data = NULL; ctx->nr_user_bufs = 0; } int io_sqe_buffers_unregister(struct io_ring_ctx *ctx) { - unsigned nr = ctx->nr_user_bufs; - int ret; - if (!ctx->buf_data) return -ENXIO; - /* - * Quiesce may unlock ->uring_lock, and while it's not held - * prevent new requests using the table. - */ - ctx->nr_user_bufs = 0; - ret = io_rsrc_ref_quiesce(ctx->buf_data, ctx); - ctx->nr_user_bufs = nr; - if (!ret) - __io_sqe_buffers_unregister(ctx); - return ret; + __io_sqe_buffers_unregister(ctx); + return 0; } /* @@ -813,7 +650,8 @@ static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages, /* check previously registered pages */ for (i = 0; i < ctx->nr_user_bufs; i++) { - struct io_mapped_ubuf *imu = ctx->user_bufs[i]; + struct io_rsrc_node *node = ctx->user_bufs[i]; + struct io_mapped_ubuf *imu = node->buf; for (j = 0; j < imu->nr_bvecs; j++) { if (!PageCompound(imu->bvec[j].bv_page)) @@ -950,21 +788,28 @@ static bool io_try_coalesce_buffer(struct page ***pages, int *nr_pages, return io_do_coalesce_buffer(pages, nr_pages, data, nr_folios); } -static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, - struct io_mapped_ubuf **pimu, - struct page **last_hpage) +static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, + struct iovec *iov, + int index, + struct page **last_hpage) { struct io_mapped_ubuf *imu = NULL; struct page **pages = NULL; + struct io_rsrc_node *node; unsigned long off; size_t size; int ret, nr_pages, i; struct io_imu_folio_data data; bool coalesced; - *pimu = (struct io_mapped_ubuf *)&dummy_ubuf; - if (!iov->iov_base) - return 0; + node = io_rsrc_node_alloc(ctx, ctx->buf_data, IORING_RSRC_BUFFER); + if (!node) + return ERR_PTR(-ENOMEM); + + if (!iov->iov_base) { + node->buf = (struct io_mapped_ubuf *) &dummy_ubuf; + return node; + } ret = -ENOMEM; pages = io_pin_pages((unsigned long) iov->iov_base, iov->iov_len, @@ -998,7 +843,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, imu->folio_shift = data.folio_shift; refcount_set(&imu->refs, 1); off = (unsigned long) iov->iov_base & ((1UL << imu->folio_shift) - 1); - *pimu = imu; + node->buf = imu; ret = 0; for (i = 0; i < nr_pages; i++) { @@ -1010,10 +855,14 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, size -= vec_len; } done: - if (ret) + if (ret) { kvfree(imu); + if (node) + io_put_rsrc_node(node); + node = ERR_PTR(ret); + } kvfree(pages); - return ret; + return node; } static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args) @@ -1037,7 +886,7 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, return -EBUSY; if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS) return -EINVAL; - ret = io_rsrc_data_alloc(ctx, IORING_RSRC_BUFFER, tags, nr_args, &data); + ret = io_rsrc_data_alloc(ctx, nr_args, &data); if (ret) return ret; ret = io_buffers_map_alloc(ctx, nr_args); @@ -1050,6 +899,9 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, memset(iov, 0, sizeof(*iov)); for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) { + struct io_rsrc_node *node; + u64 tag = 0; + if (arg) { uvec = (struct iovec __user *) arg; iov = iovec_from_user(uvec, 1, 1, &fast_iov, ctx->compat); @@ -1066,15 +918,24 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, arg += sizeof(struct iovec); } - if (!iov->iov_base && *io_get_tag_slot(data, i)) { - ret = -EINVAL; - break; + if (tags) { + if (copy_from_user(&tag, &tags[i], sizeof(tag))) { + ret = -EFAULT; + break; + } + if (tag && !iov->iov_base) { + ret = -EINVAL; + break; + } } - ret = io_sqe_buffer_register(ctx, iov, &ctx->user_bufs[i], - &last_hpage); - if (ret) + node = io_sqe_buffer_register(ctx, iov, i, &last_hpage); + if (IS_ERR(node)) { + ret = PTR_ERR(node); break; + } + node->tag = tag; + ctx->user_bufs[i] = node; } WARN_ON_ONCE(ctx->buf_data); @@ -1148,7 +1009,7 @@ int io_import_fixed(int ddir, struct iov_iter *iter, static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx) { - struct io_mapped_ubuf **user_bufs; + struct io_rsrc_node **user_bufs; struct io_rsrc_data *data; int i, ret, nbufs; @@ -1163,21 +1024,31 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx nbufs = src_ctx->nr_user_bufs; if (!nbufs) goto out_unlock; - ret = io_rsrc_data_alloc(ctx, IORING_RSRC_BUFFER, NULL, nbufs, &data); + ret = io_rsrc_data_alloc(ctx, nbufs, &data); if (ret) goto out_unlock; ret = -ENOMEM; - user_bufs = kcalloc(nbufs, sizeof(*ctx->user_bufs), GFP_KERNEL); + user_bufs = kvmalloc_array(nbufs, sizeof(struct io_rsrc_node *), + GFP_KERNEL | __GFP_ZERO); if (!user_bufs) goto out_free_data; for (i = 0; i < nbufs; i++) { - struct io_mapped_ubuf *src = src_ctx->user_bufs[i]; + struct io_mapped_ubuf *imu = src_ctx->user_bufs[i]->buf; + struct io_rsrc_node *dst_node; - if (src != &dummy_ubuf) - refcount_inc(&src->refs); - user_bufs[i] = src; + dst_node = io_rsrc_node_alloc(ctx, data, IORING_RSRC_BUFFER); + if (!dst_node) + goto out_put_free; + + if (imu == &dummy_ubuf) { + dst_node->buf = (struct io_mapped_ubuf *) &dummy_ubuf; + } else { + refcount_inc(&imu->refs); + dst_node->buf = imu; + } + user_bufs[i] = dst_node; } /* Have a ref on the bufs now, drop src lock and re-grab our own lock */ @@ -1190,12 +1061,17 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx return 0; } + mutex_unlock(&ctx->uring_lock); + mutex_lock(&src_ctx->uring_lock); /* someone raced setting up buffers, dump ours */ - for (i = 0; i < nbufs; i++) - io_buffer_unmap(ctx, &user_bufs[i]); - io_rsrc_data_free(data); - kfree(user_bufs); - return -EBUSY; + ret = -EBUSY; + i = nbufs; +out_put_free: + while (i--) { + io_buffer_unmap(src_ctx, user_bufs[i]); + kfree(user_bufs[i]); + } + kvfree(user_bufs); out_free_data: io_rsrc_data_free(data); out_unlock: diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 1589c9740083..9797dcc2a7b5 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -13,36 +13,21 @@ enum { IORING_RSRC_BUFFER = 1, }; -struct io_rsrc_put { - u64 tag; - union { - void *rsrc; - struct file *file; - struct io_mapped_ubuf *buf; - }; -}; - struct io_rsrc_data { - struct io_ring_ctx *ctx; - - u64 **tags; unsigned int nr; - u16 rsrc_type; - bool quiesce; + struct io_rsrc_node **nodes; }; struct io_rsrc_node { struct io_ring_ctx *ctx; int refs; - bool empty; u16 type; - struct list_head node; - struct io_rsrc_put item; -}; -struct io_fixed_file { - /* file * with additional FFS_* flags */ - unsigned long file_ptr; + u64 tag; + union { + unsigned long file_ptr; + struct io_mapped_ubuf *buf; + }; }; struct io_mapped_ubuf { @@ -63,21 +48,18 @@ struct io_imu_folio_data { unsigned int folio_shift; }; -void io_rsrc_node_ref_zero(struct io_rsrc_node *node); -void io_rsrc_node_destroy(struct io_ring_ctx *ctx, struct io_rsrc_node *ref_node); -struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx); -int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, void *rsrc); +struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, + struct io_rsrc_data *data, int type); +void io_free_rsrc_node(struct io_rsrc_node *node); int io_import_fixed(int ddir, struct iov_iter *iter, struct io_mapped_ubuf *imu, u64 buf_addr, size_t len); int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg); -void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx); int io_sqe_buffers_unregister(struct io_ring_ctx *ctx); int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, unsigned int nr_args, u64 __user *tags); -void __io_sqe_files_unregister(struct io_ring_ctx *ctx); int io_sqe_files_unregister(struct io_ring_ctx *ctx); int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args, u64 __user *tags); @@ -89,41 +71,23 @@ int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, unsigned int size, unsigned int type); -static inline void io_put_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node) +static inline void io_put_rsrc_node(struct io_rsrc_node *node) { - lockdep_assert_held(&ctx->uring_lock); - if (node && !--node->refs) - io_rsrc_node_ref_zero(node); -} - -static inline void __io_req_set_rsrc_node(struct io_kiocb *req, - struct io_ring_ctx *ctx) -{ - lockdep_assert_held(&ctx->uring_lock); - req->rsrc_node = ctx->rsrc_node; - ctx->rsrc_node->refs++; + io_free_rsrc_node(node); } -static inline void io_req_set_rsrc_node(struct io_kiocb *req, - struct io_ring_ctx *ctx) +static inline void io_req_put_rsrc_nodes(struct io_kiocb *req) { - if (!req->rsrc_node) - __io_req_set_rsrc_node(req, ctx); -} - -static inline u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx) -{ - unsigned int off = idx & IO_RSRC_TAG_TABLE_MASK; - unsigned int table_idx = idx >> IO_RSRC_TAG_TABLE_SHIFT; - - return &data->tags[table_idx][off]; + io_put_rsrc_node(req->rsrc_nodes[IORING_RSRC_FILE]); + io_put_rsrc_node(req->rsrc_nodes[IORING_RSRC_BUFFER]); } -static inline int io_rsrc_init(struct io_ring_ctx *ctx) +static inline void io_req_assign_rsrc_node(struct io_kiocb *req, + struct io_rsrc_node *node) { - ctx->rsrc_node = io_rsrc_node_alloc(ctx); - return ctx->rsrc_node ? 0 : -ENOMEM; + node->refs++; + req->rsrc_nodes[node->type] = node; } int io_files_update(struct io_kiocb *req, unsigned int issue_flags); diff --git a/io_uring/rw.c b/io_uring/rw.c index 8080ffd6d571..65491f4f2c7e 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -330,7 +330,7 @@ static int io_prep_rw_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe { struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); struct io_ring_ctx *ctx = req->ctx; - struct io_mapped_ubuf *imu; + struct io_rsrc_node *node; struct io_async_rw *io; u16 index; int ret; @@ -342,11 +342,11 @@ static int io_prep_rw_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe if (unlikely(req->buf_index >= ctx->nr_user_bufs)) return -EFAULT; index = array_index_nospec(req->buf_index, ctx->nr_user_bufs); - imu = ctx->user_bufs[index]; - io_req_set_rsrc_node(req, ctx); + node = ctx->user_bufs[index]; + io_req_assign_rsrc_node(req, node); io = req->async_data; - ret = io_import_fixed(ddir, &io->iter, imu, rw->addr, rw->len); + ret = io_import_fixed(ddir, &io->iter, node->buf, rw->addr, rw->len); iov_iter_save_state(&io->iter, &io->iter_state); return ret; } diff --git a/io_uring/splice.c b/io_uring/splice.c index e62bc6497a94..a0b4e0435b8b 100644 --- a/io_uring/splice.c +++ b/io_uring/splice.c @@ -51,7 +51,7 @@ void io_splice_cleanup(struct io_kiocb *req) { struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice); - io_put_rsrc_node(req->ctx, sp->rsrc_node); + io_put_rsrc_node(sp->rsrc_node); } static struct file *io_splice_get_file(struct io_kiocb *req, @@ -59,7 +59,7 @@ static struct file *io_splice_get_file(struct io_kiocb *req, { struct io_splice *sp = io_kiocb_to_cmd(req, struct io_splice); struct io_ring_ctx *ctx = req->ctx; - struct io_fixed_file *slot; + struct io_rsrc_node *node; struct file *file = NULL; if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) @@ -69,11 +69,13 @@ static struct file *io_splice_get_file(struct io_kiocb *req, if (unlikely(sp->splice_fd_in >= ctx->nr_user_files)) goto out; sp->splice_fd_in = array_index_nospec(sp->splice_fd_in, ctx->nr_user_files); - slot = &ctx->file_table.files[sp->splice_fd_in]; - if (!req->rsrc_node) - __io_req_set_rsrc_node(req, ctx); - file = io_slot_file(slot); - req->flags |= REQ_F_NEED_CLEANUP; + node = ctx->file_table.nodes[sp->splice_fd_in]; + if (node) { + node->refs++; + sp->rsrc_node = node; + file = io_slot_file(node); + req->flags |= REQ_F_NEED_CLEANUP; + } out: io_ring_submit_unlock(ctx, issue_flags); return file; diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 6994f60d7ec7..0899c71008ae 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -220,7 +220,7 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) * being called. This prevents destruction of the mapped buffer * we'll need at actual import time. */ - io_req_set_rsrc_node(req, ctx); + io_req_assign_rsrc_node(req, ctx->user_bufs[req->buf_index]); } ioucmd->cmd_op = READ_ONCE(sqe->cmd_op); @@ -276,15 +276,11 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd) { struct io_kiocb *req = cmd_to_io_kiocb(ioucmd); - struct io_ring_ctx *ctx = req->ctx; + struct io_rsrc_node *node = req->rsrc_nodes[IORING_RSRC_BUFFER]; /* Must have had rsrc_node assigned at prep time */ - if (req->rsrc_node) { - struct io_mapped_ubuf *imu; - - imu = READ_ONCE(ctx->user_bufs[req->buf_index]); - return io_import_fixed(rw, iter, imu, ubuf, len); - } + if (node) + return io_import_fixed(rw, iter, node->buf, ubuf, len); return -EFAULT; } From patchwork Tue Oct 29 15:16:36 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855091 Received: from mail-io1-f41.google.com (mail-io1-f41.google.com [209.85.166.41]) (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 B74CD1957E2 for ; Tue, 29 Oct 2024 15:23:12 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.41 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215394; cv=none; b=qdwov7NGpkr0dG/FHd3SGOmpgGmO5fDClIhq75qkCJCWR4gQwzkAeOdypp3/eRR6bfYBvjdxYJzeZqb0gxr3ZXwLlqyGPPWVaneWBkjNv4SSOkkMaskxl8On8OFT6vtKjp0tQVdkx7YY3K1CY+e2LW/V1lRhu1ybCSiX9qKiFTA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215394; c=relaxed/simple; bh=XWTjycJNGezjwQNpGO6yWqozhi9nGJETzkw/g1JhUnc=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=ZcAajUyzlM3Hq0oY9C/+uOpG8bUewxhjfGQ4HgqCAschVsl7VUlqpSsMLq5OyIhe8MmXjifev+iWGcNEgtbqmGZ1jExsnPuV/s2uT+ygHLXlZqHbehroRA3HhsxQAkYEzu8e2nc9cdksNRU1j0BwfRb0yrZSGQ495Hj3qWjPh6M= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=n39jF4pQ; arc=none smtp.client-ip=209.85.166.41 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="n39jF4pQ" Received: by mail-io1-f41.google.com with SMTP id ca18e2360f4ac-83aa3ced341so213629339f.0 for ; Tue, 29 Oct 2024 08:23:12 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215391; x=1730820191; darn=vger.kernel.org; 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=8DnQshDir80p0zue4y/aQViw49t3hlJtFYMH8XjWl8c=; b=n39jF4pQ0wphC1orvwHujuq+r9fHVAm/p0wkUpRteG8e3HO/zoUQC67nKTrFLFmcts sVqkQDG1beIIdGoZ7BphTHcNNaIk+KiQupATFzrMFRS4VvM381p76xeYcfPRn6rjQels HIoLjf2TZcYCF8cDZE0jccB5CjVmhaduXYI0fjWC8+5Fo0iDZpGytHUaZ1IypcCe1ADA qdX9NNGUBWwa8Fth1paPJwvUpriPSXlFNJKn26VWNcxwr2xSxxJjYGjHphmvnU5K0zA8 aMhjM2D6ycasNIzj5IXiA6ki9CaNlOX0Qo1vG+67TL0Byfye4+dfp8/VR/o2vkSPRrLw VaWg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215391; x=1730820191; 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=8DnQshDir80p0zue4y/aQViw49t3hlJtFYMH8XjWl8c=; b=RR4RQesznQIhFrKUr+fCn4RM9gye+DMDP5IGYlrGQPMwxLp+RBOvWXUz00/oU7hkL1 R75ymJJ/HME8AWVJUWos/Kb5Y8uuZrvvDl2NFXey/yIQ2ixo3juA0j4JcQwwPYaQGWLt w4mLVvqMjmN4ZkG4yOE23jDqmPip8Q8B0WDuVlZLatrLRQ4crCJIZWfLupL+BDi/82ir i1oVniI7SoL4e8ouxB0hTG+V/wQT9F/wrXDTEOSwYsrjc9zh1TusrJzJz/BKhN+3Ot6O C5a/wnj7JvJx+6anC0CfwY+gTrvIE4NslkCls5S9DL/Am49R7E1+BEQ0GGR5J6hp2fUw L/mA== X-Gm-Message-State: AOJu0YyDO6sdOKvJw6aFNBbKoTcp53+L8/PxbAlon1qplhnJE1qCUg50 wBOQddAPTSEyOe4XdDaas7tbe9ActOjrYq04zVah3MLhnIJSKqBjqmfoirtXBPscfRlFiRRIOQW a X-Google-Smtp-Source: AGHT+IGau73ja+HiZ0WHm5SGBK0AM3xYqxLkc0m0LdOpRN8F1LEJ9d3VxFkoaBJsI/Q6CGpKnzdPIw== X-Received: by 2002:a05:6602:641c:b0:83a:a8c6:21ad with SMTP id ca18e2360f4ac-83b1c41a25amr1139322739f.7.1730215391397; Tue, 29 Oct 2024 08:23:11 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.10 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:10 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 07/14] io_uring/rsrc: get rid of io_rsrc_node allocation cache Date: Tue, 29 Oct 2024 09:16:36 -0600 Message-ID: <20241029152249.667290-8-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 It's not going to be needed in the fast path going forward, so kill it off. Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 3 --- io_uring/io_uring.c | 6 +----- io_uring/rsrc.c | 18 ++++++------------ 3 files changed, 7 insertions(+), 20 deletions(-) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 42c5f2c992c4..696f2a05a98b 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -370,9 +370,6 @@ struct io_ring_ctx { struct io_rsrc_data *file_data; struct io_rsrc_data *buf_data; - /* protected by ->uring_lock */ - struct io_alloc_cache rsrc_node_cache; - u32 pers_next; struct xarray personalities; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 0876aa74c739..094788cca47f 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -312,9 +312,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->sqd_list); INIT_LIST_HEAD(&ctx->cq_overflow_list); INIT_LIST_HEAD(&ctx->io_buffers_cache); - ret = io_alloc_cache_init(&ctx->rsrc_node_cache, IO_NODE_ALLOC_CACHE_MAX, - sizeof(struct io_rsrc_node)); - ret |= io_alloc_cache_init(&ctx->apoll_cache, IO_POLL_ALLOC_CACHE_MAX, + ret = io_alloc_cache_init(&ctx->apoll_cache, IO_POLL_ALLOC_CACHE_MAX, sizeof(struct async_poll)); ret |= io_alloc_cache_init(&ctx->netmsg_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_msghdr)); @@ -358,7 +356,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) free_ref: percpu_ref_exit(&ctx->refs); err: - io_alloc_cache_free(&ctx->rsrc_node_cache, kfree); io_alloc_cache_free(&ctx->apoll_cache, kfree); io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free); @@ -2740,7 +2737,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); - io_alloc_cache_free(&ctx->rsrc_node_cache, kfree); if (ctx->mm_account) { mmdrop(ctx->mm_account); ctx->mm_account = NULL; diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index e32c4d1bef86..16e769ebca87 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -13,7 +13,6 @@ #include #include "io_uring.h" -#include "alloc_cache.h" #include "openclose.h" #include "rsrc.h" #include "memmap.h" @@ -130,16 +129,12 @@ struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, { struct io_rsrc_node *node; - node = io_alloc_cache_get(&ctx->rsrc_node_cache); - if (!node) { - node = kzalloc(sizeof(*node), GFP_KERNEL); - if (!node) - return NULL; + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (node) { + node->ctx = ctx; + node->refs = 1; + node->type = type; } - - node->ctx = ctx; - node->refs = 1; - node->type = type; return node; } @@ -488,8 +483,7 @@ void io_free_rsrc_node(struct io_rsrc_node *node) break; } - if (!io_alloc_cache_put(&ctx->rsrc_node_cache, node)) - kfree(node); + kfree(node); } static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) From patchwork Tue Oct 29 15:16:37 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855093 Received: from mail-io1-f47.google.com (mail-io1-f47.google.com [209.85.166.47]) (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 16ABF195985 for ; Tue, 29 Oct 2024 15:23:13 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.47 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215397; cv=none; b=qW+wePBN3Rde6D4/G7xh4xBhX9fKaVyqXcscvzdUD6sBa6UpRlbHzm7tM43bK78Z+ACHNKjCH80C806MByKERFy0zVAhdQs6hrtKatyRrzw4TrA6kzuv3lgztwI5tZ5TP0LMZbP0hX/OVct5+ENRBuZSwqAye0f2CWT7CdiC88o= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215397; c=relaxed/simple; bh=kdk/9SZ0lTDWh9ZbsRQQr7p0FUeglW/esSWNH1dFO1E=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=T9K7ysmDAJSWMK8+nsqSP7+mz6gYmMEjVtmZLZmCx6trYm7lQbAa6Yzjuvd681jnZwuvjSjnsjWFp7gNOAYzjrWKA30xtiJqOuRu7sFsSKBtX4Zo8PkV0oqbgd+8ZJjqMREhr24mPxPAloNDZsPWUb7zXX0G0HrRZAYYPagFcpU= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=LNk3sETZ; arc=none smtp.client-ip=209.85.166.47 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="LNk3sETZ" Received: by mail-io1-f47.google.com with SMTP id ca18e2360f4ac-83abcfb9f37so219900139f.1 for ; Tue, 29 Oct 2024 08:23:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215393; x=1730820193; darn=vger.kernel.org; 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=YOe3sTWaIirEpBGKzV9oeCe6wFtUn4hw4nwiG1m0gT0=; b=LNk3sETZ4x/2wI5Twi9OzplYk5BbLwB/1xxc2U4KOW8WEGQ8e6/NISK53piDu4w2q/ ka1QH7ahazMd3tcZ5Lq1U26RKaEm8xUqeL5bvPkF3eda7HZU/AsN+aBrHjORmiWPa+Cr Gh7f5thXgjseOxX/KlU08xzeP8wj0quVmr+xBgxN1/HCkSc88rMipY+dC5qsRFkuVtrS x0+qVSn3vnuNGNf2HUtbAjPlpg8f079DI1/8d4Yenv5U1Pw0jwvnmX0dUOFocGc8pdb4 o8jQi/7NToISINoofG54mwUGPi9/uByIsFd8452dZcXSPqX2OYkYkfIywIU4fyGmlPDF 1sGw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215393; x=1730820193; 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=YOe3sTWaIirEpBGKzV9oeCe6wFtUn4hw4nwiG1m0gT0=; b=nuKJxnK/quxlmpXjl1oZRX7aTetI4Snd7vEATNG7icrk8QMtA1/yp0MG88V+szPRNI iV9ITYRcM/a8lUa1a7YT25v3rer+NKg5He7NzbReAJiZh1IfsfwENovLmLG0k8vXcjEo 41YXEudM87lrJkMqKFUBYEJ0oRFL8BwO/Ueu9zKqZMC36A+OT3Pyz3UV7ttranPdvzw2 PHzPjFxMrME0BV4ZFJPBLNHFky+FcpsYytA+JfrFNPq95zJAESUhQ8wFKrBBBNuduZrw ourUKqt7ghwWlBrrK36bD58dzXbwNO3RfhwnpdDnLex2gqpz+qjgwPSvTB/jTyeq8Uwh RniQ== X-Gm-Message-State: AOJu0YyEhhlc3H7JPyj5FW0IG3+81uC7MIBKnysTfo6mIaPcQ+CDb4wz M25Qbxtkk9O/6XF1XHQGnTdOwqHwqXXPGFBfQ0xRWoVbWijtazILabTiYICZaaYyfg+IdlDOpcF M X-Google-Smtp-Source: AGHT+IHi67Gi0RDfvGOuVqfVCCymVUd+0YkCTuuzoHKHTDQoBECUKN4+o0aMWbkIo+NVNeEk2aiDNg== X-Received: by 2002:a05:6602:1589:b0:837:7d54:acf1 with SMTP id ca18e2360f4ac-83b1c3b7c50mr1150305239f.2.1730215392801; Tue, 29 Oct 2024 08:23:12 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.11 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:11 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 08/14] io_uring/rsrc: add an empty io_rsrc_node for sparse buffer entries Date: Tue, 29 Oct 2024 09:16:37 -0600 Message-ID: <20241029152249.667290-9-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Rather than allocate an io_rsrc_node for an empty/sparse buffer entry, add a const entry that can be used for that. This just needs checking for writing the tag, and the put check needs to check for that sparse node rather than NULL for validity. This avoids allocating rsrc nodes for sparse buffer entries. Signed-off-by: Jens Axboe --- io_uring/io_uring.c | 4 ++-- io_uring/notif.c | 4 ++-- io_uring/rsrc.c | 49 ++++++++++++++++++++++++++------------------- io_uring/rsrc.h | 11 +++++++--- io_uring/splice.c | 2 +- 5 files changed, 41 insertions(+), 29 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 094788cca47f..9282d5fa45d3 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2032,8 +2032,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->flags = (__force io_req_flags_t) sqe_flags; req->cqe.user_data = READ_ONCE(sqe->user_data); req->file = NULL; - req->rsrc_nodes[IORING_RSRC_FILE] = NULL; - req->rsrc_nodes[IORING_RSRC_BUFFER] = NULL; + req->rsrc_nodes[IORING_RSRC_FILE] = rsrc_empty_node; + req->rsrc_nodes[IORING_RSRC_BUFFER] = rsrc_empty_node; req->task = current; req->cancel_seq_set = false; diff --git a/io_uring/notif.c b/io_uring/notif.c index 4f02e969cf08..44bf21c0f810 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -117,8 +117,8 @@ struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx) notif->file = NULL; notif->task = current; io_get_task_refs(1); - notif->rsrc_nodes[IORING_RSRC_FILE] = NULL; - notif->rsrc_nodes[IORING_RSRC_BUFFER] = NULL; + notif->rsrc_nodes[IORING_RSRC_FILE] = rsrc_empty_node; + notif->rsrc_nodes[IORING_RSRC_BUFFER] = rsrc_empty_node; nd = io_notif_to_data(notif); nd->zc_report = false; diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 16e769ebca87..b1729cbdc749 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -38,6 +38,11 @@ static const struct io_mapped_ubuf dummy_ubuf = { .len = UINT_MAX, }; +const struct io_rsrc_node empty_node = { + .type = IORING_RSRC_BUFFER, + .buf = (struct io_mapped_ubuf *) &dummy_ubuf, +}; + int __io_account_mem(struct user_struct *user, unsigned long nr_pages) { unsigned long page_limit, cur_pages, new_pages; @@ -145,7 +150,8 @@ static void io_rsrc_data_free(struct io_rsrc_data *data) for (i = 0; i < data->nr; i++) { struct io_rsrc_node *node = data->nodes[i]; - io_put_rsrc_node(node); + if (node) + io_put_rsrc_node(node); } kvfree(data->nodes); kfree(data); @@ -230,7 +236,8 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, break; } ctx->file_table.nodes[i] = node; - node->tag = tag; + if (tag) + node->tag = tag; io_fixed_file_set(node, file); io_file_bitmap_set(&ctx->file_table, i); } @@ -282,10 +289,12 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, err = PTR_ERR(node); break; } - io_put_rsrc_node(ctx->user_bufs[i]); + if (ctx->user_bufs[i]) + io_put_rsrc_node(ctx->user_bufs[i]); ctx->user_bufs[i] = node; - node->tag = tag; + if (tag) + node->tag = tag; if (ctx->compat) user_data += sizeof(struct compat_iovec); else @@ -601,8 +610,10 @@ static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx) lockdep_assert_held(&ctx->uring_lock); for (i = 0; i < ctx->nr_user_bufs; i++) { - io_put_rsrc_node(ctx->user_bufs[i]); - ctx->user_bufs[i] = NULL; + if (ctx->user_bufs[i]) { + io_put_rsrc_node(ctx->user_bufs[i]); + ctx->user_bufs[i] = NULL; + } } kvfree(ctx->user_bufs); ctx->user_bufs = NULL; @@ -800,11 +811,6 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, if (!node) return ERR_PTR(-ENOMEM); - if (!iov->iov_base) { - node->buf = (struct io_mapped_ubuf *) &dummy_ubuf; - return node; - } - ret = -ENOMEM; pages = io_pin_pages((unsigned long) iov->iov_base, iov->iov_len, &nr_pages); @@ -928,7 +934,8 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, ret = PTR_ERR(node); break; } - node->tag = tag; + if (tag) + node->tag = tag; ctx->user_bufs[i] = node; } @@ -1029,18 +1036,18 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx goto out_free_data; for (i = 0; i < nbufs; i++) { - struct io_mapped_ubuf *imu = src_ctx->user_bufs[i]->buf; + struct io_rsrc_node *src_node = src_ctx->user_bufs[i]; struct io_rsrc_node *dst_node; - dst_node = io_rsrc_node_alloc(ctx, data, IORING_RSRC_BUFFER); - if (!dst_node) - goto out_put_free; - - if (imu == &dummy_ubuf) { - dst_node->buf = (struct io_mapped_ubuf *) &dummy_ubuf; + if (src_node == rsrc_empty_node) { + dst_node = rsrc_empty_node; } else { - refcount_inc(&imu->refs); - dst_node->buf = imu; + dst_node = io_rsrc_node_alloc(ctx, data, IORING_RSRC_BUFFER); + if (!dst_node) + goto out_put_free; + + refcount_inc(&src_node->buf->refs); + dst_node->buf = src_node->buf; } user_bufs[i] = dst_node; } diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 9797dcc2a7b5..db04d04d4799 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -71,9 +71,12 @@ int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, unsigned int size, unsigned int type); +extern const struct io_rsrc_node empty_node; +#define rsrc_empty_node (struct io_rsrc_node *) &empty_node + static inline void io_put_rsrc_node(struct io_rsrc_node *node) { - if (node && !--node->refs) + if (node != rsrc_empty_node && !--node->refs) io_free_rsrc_node(node); } @@ -86,8 +89,10 @@ static inline void io_req_put_rsrc_nodes(struct io_kiocb *req) static inline void io_req_assign_rsrc_node(struct io_kiocb *req, struct io_rsrc_node *node) { - node->refs++; - req->rsrc_nodes[node->type] = node; + if (node != rsrc_empty_node) { + node->refs++; + req->rsrc_nodes[node->type] = node; + } } int io_files_update(struct io_kiocb *req, unsigned int issue_flags); diff --git a/io_uring/splice.c b/io_uring/splice.c index a0b4e0435b8b..f78afb575ae6 100644 --- a/io_uring/splice.c +++ b/io_uring/splice.c @@ -35,7 +35,7 @@ static int __io_splice_prep(struct io_kiocb *req, if (unlikely(sp->flags & ~valid_flags)) return -EINVAL; sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); - sp->rsrc_node = NULL; + sp->rsrc_node = rsrc_empty_node; req->flags |= REQ_F_FORCE_ASYNC; return 0; } From patchwork Tue Oct 29 15:16:38 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855092 Received: from mail-io1-f48.google.com (mail-io1-f48.google.com [209.85.166.48]) (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 582C91957E2 for ; Tue, 29 Oct 2024 15:23:15 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.48 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215397; cv=none; b=S6REgANBaH3vKqXOk6aAEhPCdhMVFgrYwzuhS41VKk9zncx7wA6uIqDKGUXoFNlybdPcKxbBzucRDvS/6+1fSoBTbmwps82UF/K/7BrnK/Obch0wVf1XrNYtRejiuHX+vgzlqD9gzgQ2xpfgqMu8B1uiCtG403kly122iBev2hI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215397; c=relaxed/simple; bh=lkzxSGPhE74nEna4hhBDxfxOMVtN4Eja2fRQ8mJUNWo=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=eC853yJHwgNh5ZeMwP15vSNICO4R993KYNSsNLrfnEH5yI8jQNLNhy88f69Yz9lI9ETP38XHGxCdFGUg5L2/su1AIyI3jIeVxxX61chicTg5oj5YXJcAIpri8zy6kCXb9yUv1Q8JqEA/F4c1wTv9oggGqGKX2o5Zv80q7PVtFcY= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=yQW+Pycr; arc=none smtp.client-ip=209.85.166.48 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="yQW+Pycr" Received: by mail-io1-f48.google.com with SMTP id ca18e2360f4ac-83aa3ced341so213630539f.0 for ; Tue, 29 Oct 2024 08:23:15 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215394; x=1730820194; darn=vger.kernel.org; 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=Jx0+s/FuypCRBo+RK3Xr0Fm1dzG80IoiEOq/Q+n3Eik=; b=yQW+Pycr6UFbOWnyJExYECR1q4UaiAl2pm1cNKFKCHKAkRfJYXNmBMwyI3SfI+i0/C 2/hFdWClToPtBbUXYw3qSZEIiDwdJGCErtCIamf/NVxN5bZROd8PwfqxAyhqrP4ost33 2c9+SGgsq6/IFvHYI/f8p2g1Bv66ROTfZuWK/IkfKclj5GgBV5iJjD+g5yF6ebFe2FUO mHg2LQ4kP7U8hQkcz5HSGsnx9I2hfxUmJF+UUMRP4dYisiYV3e61re6HuJXEIPHZ/CVw 2Mthq1xMTOXl2RDLOVmu2KFfuuUrc0cIEWAd+zFegBb/XKPJYHLzsRcv/C+tEX+RGLTd qCBA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215394; x=1730820194; 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=Jx0+s/FuypCRBo+RK3Xr0Fm1dzG80IoiEOq/Q+n3Eik=; b=rbWEnN5wTjCeSJPTLHWRucWO8f6dOqBDuU2rTIy6xF74OWC1oyuoltBSj7kGHfixHK rFef2RKqL7lWttF/SGVMLj3Ly2E3W/vcmXKs+giG8JgTengO8Zl5CU7aDNs3SK7kTVo0 q+sTUDEbjMA5tj7k2/Sb6orLB9gqt53dFoPFOs2HVq8WgfmGy8nNp997sG1WVdu0vt0U FvR89/sS1E51ywIGRqFB5G4LSrYiA7IfiOLrHnM/Lv2oVFzmRJ8R5Se3CUh6evCXvOjR k+FEvIwTo2K2UhEZHIiate2c6EIR3Xy9Ea+XuOBtmbZGUiQhVxZYOCrfDOHRkFAZaNMf KYaw== X-Gm-Message-State: AOJu0YwjdwKmEoHDQ8KLEc0ZdqOEI/LAJ16jSSDfcb05wGvcIM/PzS7X rBoEuyUnoRr24IYEau9cef7VlJLsjeUDSJU/Xh0FgMNSxaLsMYvZ8JrSwa0dnwCEcGNTdLfa0Si 7 X-Google-Smtp-Source: AGHT+IGRY+yogxpysuuwYWJPRY0gcrg9WQGX5VIC1nO5YRPPFH/gegjvROZac8zUkZrx107sYNNAdg== X-Received: by 2002:a05:6602:29c4:b0:83a:a8ac:a2bc with SMTP id ca18e2360f4ac-83b1c5fd3f0mr1311469039f.16.1730215394015; Tue, 29 Oct 2024 08:23:14 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.12 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:13 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 09/14] io_uring: only initialize io_kiocb rsrc_nodes when needed Date: Tue, 29 Oct 2024 09:16:38 -0600 Message-ID: <20241029152249.667290-10-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Add the empty node initializing to the preinit part of the io_kiocb allocation, and reset them if they have been used. Signed-off-by: Jens Axboe --- io_uring/io_uring.c | 4 ++-- io_uring/rsrc.h | 10 ++++++++-- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 9282d5fa45d3..60c947114fa3 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -947,6 +947,8 @@ void io_req_defer_failed(struct io_kiocb *req, s32 res) static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx) { req->ctx = ctx; + req->rsrc_nodes[IORING_RSRC_FILE] = rsrc_empty_node; + req->rsrc_nodes[IORING_RSRC_BUFFER] = rsrc_empty_node; req->link = NULL; req->async_data = NULL; /* not necessary, but safer to zero */ @@ -2032,8 +2034,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->flags = (__force io_req_flags_t) sqe_flags; req->cqe.user_data = READ_ONCE(sqe->user_data); req->file = NULL; - req->rsrc_nodes[IORING_RSRC_FILE] = rsrc_empty_node; - req->rsrc_nodes[IORING_RSRC_BUFFER] = rsrc_empty_node; req->task = current; req->cancel_seq_set = false; diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index db04d04d4799..6a7863f13ea9 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -82,8 +82,14 @@ static inline void io_put_rsrc_node(struct io_rsrc_node *node) static inline void io_req_put_rsrc_nodes(struct io_kiocb *req) { - io_put_rsrc_node(req->rsrc_nodes[IORING_RSRC_FILE]); - io_put_rsrc_node(req->rsrc_nodes[IORING_RSRC_BUFFER]); + if (req->rsrc_nodes[IORING_RSRC_FILE] != rsrc_empty_node) { + io_put_rsrc_node(req->rsrc_nodes[IORING_RSRC_FILE]); + req->rsrc_nodes[IORING_RSRC_FILE] = rsrc_empty_node; + } + if (req->rsrc_nodes[IORING_RSRC_BUFFER] != rsrc_empty_node) { + io_put_rsrc_node(req->rsrc_nodes[IORING_RSRC_BUFFER]); + req->rsrc_nodes[IORING_RSRC_BUFFER] = rsrc_empty_node; + } } static inline void io_req_assign_rsrc_node(struct io_kiocb *req, From patchwork Tue Oct 29 15:16:39 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855098 Received: from mail-io1-f49.google.com (mail-io1-f49.google.com [209.85.166.49]) (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 91416192D73 for ; Tue, 29 Oct 2024 15:23:16 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.49 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215402; cv=none; b=mrbOSljVIeYY3LYXsd7bHXINMIStyx+heKpdwRb/kV/s3VbcQV77lnQ3lDdP+QrPFJ7MJycTAnL0AUwDOY6Btb+Z6FHrb5sioaH4epYHimj3QJ63Sewo1lnhI/wAAK6N/9q6Rmbk2S9eiaMJiD+pLB05fkb3KFVYT2T+05u8unY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215402; c=relaxed/simple; bh=rF1F7mRg81r1JZfeQMFyR0YxBXBG2Sz7+aVnWOxyr6A=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=EpwV4/cuOu76Ezf5tSfb1Fj5KGEOy/Mfy5IiT/i0IWArewWHs8epNujRmzcyhr++IAmosAwg17JXmiJ8oFeID+iwNBX3VHzg/u0PG7UrdsNpKqM9OhH7YjkRnHR1g6jseGXUxglpooFxFE2EiHGhYGcxQY1loHQNsHmAZc9YfhE= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=xq7WE511; arc=none smtp.client-ip=209.85.166.49 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="xq7WE511" Received: by mail-io1-f49.google.com with SMTP id ca18e2360f4ac-83ab5b4b048so224284239f.2 for ; Tue, 29 Oct 2024 08:23:16 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215396; x=1730820196; darn=vger.kernel.org; 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=KZHSdILI2GyI3B5u8oG+vmRZl/98vI9kPJoHRTFnMvg=; b=xq7WE511wtXCuRbEr3KZmlrLll0XQM8r9MmC//Kp2iJqbIyVT25ec8/6yONYWuYuil sdiaqMijbiQrZtIP4LI7OQhSIT/GzTflTUT9EoEdWqKrffqepiyZAQUYdiQ6sJt7/Cp8 J2dMHMESJoVUx9CrDpjCZSQ9QVZiRgWBmvpYcwGo6bVNhzaNsR+fyKbwJkccefBtxJv6 2AbUMBezabHdoHfQ7KjjVicBfp0dgPHV/D8mcaQYgYQsDepVZMiA5ZUYF5uBM8DfR8HW j9yfsc8K8x0RVY+2G8DSK3w9/6FI+4o/OgIUjAWyVMzhY5HI7ngz382/DKzygzjtceVc GX+w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215396; x=1730820196; 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=KZHSdILI2GyI3B5u8oG+vmRZl/98vI9kPJoHRTFnMvg=; b=AjWMjjvG81soPArjAIfTI13g8WAfQ7hVAe6AvU5odHOCmmq23QLO3tZjmZZS2v3/pg bH3cdNG7QIPVWUiw7g3IDYyFQc6Z/uOj6/YjD4SqSV15Hz2ZqSyRSLs3t4dV8BFPKaXE SSgqm42ko7FMwyHj7PIRGNgcfq0MqUQ5Yd/ztyH3VjTGvz1mTy54UOZgjmvX0aZ/aoOf n7audm16Gv+AWrg5ZOJqx5OikCUtkv9Rq05zw1aEythAveiVznm8+JnLG5EKHWSqS5Ro 5CkGZxtSeeEcec9x2Iag46yn+U5oJEQstN4X0AVfUZ6p+lX2LsAhF9T0lmr24jWqEvKY Pnog== X-Gm-Message-State: AOJu0YyXch4/J2+y7vyi72WktHqBk+mme8XYchW40XWx4DepX2wWOyYr ve68OvMuNYa5Z/ZO7acGPg67SIpRXucLYkRWFXYJZQmPF/4yn7p4jtVNki/qmG4HfAy/ti0E4zo o X-Google-Smtp-Source: AGHT+IGPBKMiQ6Od3LlaxL1aOMFsa3/6D08XHXikPDFqcIOCzxW0xuHVOJ+StfLAJIahuXKoFdVPeg== X-Received: by 2002:a05:6602:14cb:b0:835:3ffe:fe31 with SMTP id ca18e2360f4ac-83b1c40b3a5mr1182752039f.8.1730215395479; Tue, 29 Oct 2024 08:23:15 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.14 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:14 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 10/14] io_uring/rsrc: unify file and buffer resource tables Date: Tue, 29 Oct 2024 09:16:39 -0600 Message-ID: <20241029152249.667290-11-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 For files, there's nr_user_files/file_table/file_data, and buffers have nr_user_bufs/user_bufs/buf_data. There's no reason why file_table and file_data can't be the same thing, and ditto for the buffer side. That gets rid of more io_ring_ctx state that's in two spots rather than just being in one spot, as it should be. Put all the registered file data in one locations, and ditto on the buffer front. This also avoids having both io_rsrc_data->nodes being an allocated array, and ->user_bufs[] or ->file_table.nodes. There's no reason to have this information duplicated. Keep it in one spot, io_rsrc_data, along with how many resources are available. Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 15 ++- io_uring/cancel.c | 4 +- io_uring/fdinfo.c | 10 +- io_uring/filetable.c | 46 +++---- io_uring/filetable.h | 2 +- io_uring/io_uring.c | 7 +- io_uring/msg_ring.c | 4 +- io_uring/net.c | 6 +- io_uring/nop.c | 6 +- io_uring/register.c | 3 +- io_uring/rsrc.c | 215 +++++++++++---------------------- io_uring/rsrc.h | 7 +- io_uring/rw.c | 6 +- io_uring/splice.c | 6 +- io_uring/uring_cmd.c | 6 +- 15 files changed, 127 insertions(+), 216 deletions(-) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 696f2a05a98b..77fd508d043a 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -55,8 +55,13 @@ struct io_wq_work { int cancel_seq; }; +struct io_rsrc_data { + unsigned int nr; + struct io_rsrc_node **nodes; +}; + struct io_file_table { - struct io_rsrc_node **nodes; + struct io_rsrc_data data; unsigned long *bitmap; unsigned int alloc_hint; }; @@ -276,9 +281,7 @@ struct io_ring_ctx { struct io_wq_work_list iopoll_list; struct io_file_table file_table; - struct io_rsrc_node **user_bufs; - unsigned nr_user_files; - unsigned nr_user_bufs; + struct io_rsrc_data buf_table; struct io_submit_state submit_state; @@ -366,10 +369,6 @@ struct io_ring_ctx { struct wait_queue_head poll_wq; struct io_restriction restrictions; - /* slow path rsrc auxilary data, used by update/register */ - struct io_rsrc_data *file_data; - struct io_rsrc_data *buf_data; - u32 pers_next; struct xarray personalities; diff --git a/io_uring/cancel.c b/io_uring/cancel.c index cc3475b22ae5..3a2996307025 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -240,9 +240,9 @@ static int __io_sync_cancel(struct io_uring_task *tctx, /* fixed must be grabbed every time since we drop the uring_lock */ if ((cd->flags & IORING_ASYNC_CANCEL_FD) && (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) { - if (unlikely(fd >= ctx->nr_user_files)) + if (unlikely(fd >= ctx->file_table.data.nr)) return -EBADF; - fd = array_index_nospec(fd, ctx->nr_user_files); + fd = array_index_nospec(fd, ctx->file_table.data.nr); cd->file = io_file_from_index(&ctx->file_table, fd); if (!cd->file) return -EBADF; diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index 064a79475c5f..e3f5e9fe5562 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -165,8 +165,8 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu); seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time); seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time); - seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); - for (i = 0; has_lock && i < ctx->nr_user_files; i++) { + seq_printf(m, "UserFiles:\t%u\n", ctx->file_table.data.nr); + for (i = 0; has_lock && i < ctx->file_table.data.nr; i++) { struct file *f = io_file_from_index(&ctx->file_table, i); if (f) @@ -174,9 +174,9 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) else seq_printf(m, "%5u: \n", i); } - seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); - for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) { - struct io_mapped_ubuf *buf = ctx->user_bufs[i]->buf; + seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.nr); + for (i = 0; has_lock && i < ctx->buf_table.nr; i++) { + struct io_mapped_ubuf *buf = ctx->buf_table.nodes[i]->buf; seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, buf->len); } diff --git a/io_uring/filetable.c b/io_uring/filetable.c index a01be324ac15..c1bea2d9dce2 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -38,25 +38,19 @@ static int io_file_bitmap_get(struct io_ring_ctx *ctx) bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) { - table->nodes = kvmalloc_array(nr_files, sizeof(struct io_src_node *), - GFP_KERNEL_ACCOUNT | __GFP_ZERO); - if (unlikely(!table->nodes)) + if (io_rsrc_data_alloc(&table->data, nr_files)) return false; - table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT); - if (unlikely(!table->bitmap)) { - kvfree(table->nodes); - return false; - } - - return true; + if (table->bitmap) + return true; + io_rsrc_data_free(&table->data); + return false; } void io_free_file_tables(struct io_file_table *table) { - kvfree(table->nodes); + io_rsrc_data_free(&table->data); bitmap_free(table->bitmap); - table->nodes = NULL; table->bitmap = NULL; } @@ -68,22 +62,22 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, if (io_is_uring_fops(file)) return -EBADF; - if (!ctx->file_data) + if (!ctx->file_table.data.nr) return -ENXIO; - if (slot_index >= ctx->nr_user_files) + if (slot_index >= ctx->file_table.data.nr) return -EINVAL; - node = io_rsrc_node_alloc(ctx, ctx->file_data, IORING_RSRC_FILE); + node = io_rsrc_node_alloc(ctx, &ctx->file_table.data, IORING_RSRC_FILE); if (IS_ERR(node)) return -ENOMEM; - slot_index = array_index_nospec(slot_index, ctx->nr_user_files); - if (ctx->file_table.nodes[slot_index]) - io_put_rsrc_node(ctx->file_table.nodes[slot_index]); + slot_index = array_index_nospec(slot_index, ctx->file_table.data.nr); + if (ctx->file_table.data.nodes[slot_index]) + io_put_rsrc_node(ctx->file_table.data.nodes[slot_index]); else io_file_bitmap_set(&ctx->file_table, slot_index); - ctx->file_table.nodes[slot_index] = node; + ctx->file_table.data.nodes[slot_index] = node; io_fixed_file_set(node, file); return 0; } @@ -129,16 +123,16 @@ int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags, int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset) { - if (unlikely(!ctx->file_data)) + if (unlikely(!ctx->file_table.data.nr)) return -ENXIO; - if (offset >= ctx->nr_user_files) + if (offset >= ctx->file_table.data.nr) return -EINVAL; - offset = array_index_nospec(offset, ctx->nr_user_files); - if (!ctx->file_table.nodes[offset]) + offset = array_index_nospec(offset, ctx->file_table.data.nr); + if (!ctx->file_table.data.nodes[offset]) return -EBADF; - io_put_rsrc_node(ctx->file_table.nodes[offset]); - ctx->file_table.nodes[offset] = NULL; + io_put_rsrc_node(ctx->file_table.data.nodes[offset]); + ctx->file_table.data.nodes[offset] = NULL; io_file_bitmap_clear(&ctx->file_table, offset); return 0; } @@ -153,7 +147,7 @@ int io_register_file_alloc_range(struct io_ring_ctx *ctx, return -EFAULT; if (check_add_overflow(range.off, range.len, &end)) return -EOVERFLOW; - if (range.resv || end > ctx->nr_user_files) + if (range.resv || end > ctx->file_table.data.nr) return -EINVAL; io_file_table_set_alloc_range(ctx, range.off, range.len); diff --git a/io_uring/filetable.h b/io_uring/filetable.h index 47616079abaa..664c31502dbb 100644 --- a/io_uring/filetable.h +++ b/io_uring/filetable.h @@ -52,7 +52,7 @@ static inline struct file *io_slot_file(struct io_rsrc_node *node) static inline struct file *io_file_from_index(struct io_file_table *table, int index) { - struct io_rsrc_node *node = table->nodes[index]; + struct io_rsrc_node *node = table->data.nodes[index]; if (node) return io_slot_file(node); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 60c947114fa3..78df515fb3a7 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1879,11 +1879,10 @@ inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, struct file *file = NULL; io_ring_submit_lock(ctx, issue_flags); - - if (unlikely((unsigned int)fd >= ctx->nr_user_files)) + if (unlikely((unsigned int)fd >= ctx->file_table.data.nr)) goto out; - fd = array_index_nospec(fd, ctx->nr_user_files); - node = ctx->file_table.nodes[fd]; + fd = array_index_nospec(fd, ctx->file_table.data.nr); + node = ctx->file_table.data.nodes[fd]; if (node) { io_req_assign_rsrc_node(req, node); req->flags |= io_slot_flags(node); diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index edea1ffd501c..b90ab3b8f5e0 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -180,8 +180,8 @@ static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_fl int idx = msg->src_fd; io_ring_submit_lock(ctx, issue_flags); - if (likely(idx < ctx->nr_user_files)) { - idx = array_index_nospec(idx, ctx->nr_user_files); + if (likely(idx < ctx->file_table.data.nr)) { + idx = array_index_nospec(idx, ctx->file_table.data.nr); file = io_file_from_index(&ctx->file_table, idx); if (file) get_file(file); diff --git a/io_uring/net.c b/io_uring/net.c index ce1156551d10..3e1f31574abb 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1347,9 +1347,9 @@ static int io_send_zc_import(struct io_kiocb *req, unsigned int issue_flags) ret = -EFAULT; io_ring_submit_lock(ctx, issue_flags); - if (sr->buf_index < ctx->nr_user_bufs) { - idx = array_index_nospec(sr->buf_index, ctx->nr_user_bufs); - node = ctx->user_bufs[idx]; + if (sr->buf_index < ctx->buf_table.nr) { + idx = array_index_nospec(sr->buf_index, ctx->buf_table.nr); + node = ctx->buf_table.nodes[idx]; io_req_assign_rsrc_node(sr->notif, node); ret = 0; } diff --git a/io_uring/nop.c b/io_uring/nop.c index de91600a3bc6..0dac01127de5 100644 --- a/io_uring/nop.c +++ b/io_uring/nop.c @@ -66,9 +66,9 @@ int io_nop(struct io_kiocb *req, unsigned int issue_flags) ret = -EFAULT; io_ring_submit_lock(ctx, issue_flags); - if (nop->buffer < ctx->nr_user_bufs) { - idx = array_index_nospec(nop->buffer, ctx->nr_user_bufs); - node = READ_ONCE(ctx->user_bufs[idx]); + if (nop->buffer < ctx->buf_table.nr) { + idx = array_index_nospec(nop->buffer, ctx->buf_table.nr); + node = READ_ONCE(ctx->buf_table.nodes[idx]); io_req_assign_rsrc_node(req, node); ret = 0; } diff --git a/io_uring/register.c b/io_uring/register.c index 1eb686eaa310..45edfc57963a 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -937,7 +937,8 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, mutex_lock(&ctx->uring_lock); ret = __io_uring_register(ctx, opcode, arg, nr_args); mutex_unlock(&ctx->uring_lock); - trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, ret); + trace_io_uring_register(ctx, opcode, ctx->file_table.data.nr, + ctx->buf_table.nr, ret); if (!use_registered_ring) fput(file); return ret; diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index b1729cbdc749..902e003704a9 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -143,39 +143,28 @@ struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, return node; } -static void io_rsrc_data_free(struct io_rsrc_data *data) +__cold void io_rsrc_data_free(struct io_rsrc_data *data) { - int i; - - for (i = 0; i < data->nr; i++) { - struct io_rsrc_node *node = data->nodes[i]; - - if (node) - io_put_rsrc_node(node); + if (!data->nr) + return; + while (data->nr--) { + if (data->nodes[data->nr]) + io_put_rsrc_node(data->nodes[data->nr]); } kvfree(data->nodes); - kfree(data); + data->nodes = NULL; + data->nr = 0; } -__cold static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, unsigned nr, - struct io_rsrc_data **pdata) +__cold int io_rsrc_data_alloc(struct io_rsrc_data *data, unsigned nr) { - struct io_rsrc_data *data; - - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - return -ENOMEM; - data->nodes = kvmalloc_array(nr, sizeof(struct io_rsrc_node *), - GFP_KERNEL | __GFP_ZERO); - if (!data->nodes) { - kfree(data); - return -ENOMEM; + GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (data->nodes) { + data->nr = nr; + return 0; } - - data->nr = nr; - *pdata = data; - return 0; + return -ENOMEM; } static int __io_sqe_files_update(struct io_ring_ctx *ctx, @@ -187,9 +176,9 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, int fd, i, err = 0; unsigned int done; - if (!ctx->file_data) + if (!ctx->file_table.data.nr) return -ENXIO; - if (up->offset + nr_args > ctx->nr_user_files) + if (up->offset + nr_args > ctx->file_table.data.nr) return -EINVAL; for (done = 0; done < nr_args; done++) { @@ -207,10 +196,10 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (fd == IORING_REGISTER_FILES_SKIP) continue; - i = array_index_nospec(up->offset + done, ctx->nr_user_files); - if (ctx->file_table.nodes[i]) { - io_put_rsrc_node(ctx->file_table.nodes[i]); - ctx->file_table.nodes[i] = NULL; + i = array_index_nospec(up->offset + done, ctx->file_table.data.nr); + if (ctx->file_table.data.nodes[i]) { + io_put_rsrc_node(ctx->file_table.data.nodes[i]); + ctx->file_table.data.nodes[i] = NULL; io_file_bitmap_clear(&ctx->file_table, i); } if (fd != -1) { @@ -229,13 +218,14 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - node = io_rsrc_node_alloc(ctx, ctx->file_data, IORING_RSRC_FILE); + node = io_rsrc_node_alloc(ctx, &ctx->file_table.data, + IORING_RSRC_FILE); if (!node) { err = -ENOMEM; fput(file); break; } - ctx->file_table.nodes[i] = node; + ctx->file_table.data.nodes[i] = node; if (tag) node->tag = tag; io_fixed_file_set(node, file); @@ -257,9 +247,9 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, __u32 done; int i, err; - if (!ctx->buf_data) + if (!ctx->buf_table.nr) return -ENXIO; - if (up->offset + nr_args > ctx->nr_user_bufs) + if (up->offset + nr_args > ctx->buf_table.nr) return -EINVAL; for (done = 0; done < nr_args; done++) { @@ -283,16 +273,16 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, err = -EINVAL; break; } - i = array_index_nospec(up->offset + done, ctx->nr_user_bufs); + i = array_index_nospec(up->offset + done, ctx->buf_table.nr); node = io_sqe_buffer_register(ctx, iov, i, &last_hpage); if (IS_ERR(node)) { err = PTR_ERR(node); break; } - if (ctx->user_bufs[i]) - io_put_rsrc_node(ctx->user_bufs[i]); + if (ctx->buf_table.nodes[i]) + io_put_rsrc_node(ctx->buf_table.nodes[i]); - ctx->user_bufs[i] = node; + ctx->buf_table.nodes[i] = node; if (tag) node->tag = tag; if (ctx->compat) @@ -410,7 +400,7 @@ static int io_files_update_with_index_alloc(struct io_kiocb *req, struct file *file; int ret, fd; - if (!req->ctx->file_data) + if (!req->ctx->file_table.data.nr) return -ENXIO; for (done = 0; done < up->nr_args; done++) { @@ -495,35 +485,13 @@ void io_free_rsrc_node(struct io_rsrc_node *node) kfree(node); } -static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) -{ - int i; - - lockdep_assert_held(&ctx->uring_lock); - - for (i = 0; i < ctx->nr_user_files; i++) { - struct io_rsrc_node *node = ctx->file_table.nodes[i]; - - if (node) { - io_put_rsrc_node(node); - io_file_bitmap_clear(&ctx->file_table, i); - ctx->file_table.nodes[i] = NULL; - } - } - - io_free_file_tables(&ctx->file_table); - io_file_table_set_alloc_range(ctx, 0, 0); - io_rsrc_data_free(ctx->file_data); - ctx->file_data = NULL; - ctx->nr_user_files = 0; -} - int io_sqe_files_unregister(struct io_ring_ctx *ctx) { - if (!ctx->file_data) + if (!ctx->file_table.data.nr) return -ENXIO; - __io_sqe_files_unregister(ctx); + io_free_file_tables(&ctx->file_table); + io_file_table_set_alloc_range(ctx, 0, 0); return 0; } @@ -535,7 +503,7 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, int fd, ret; unsigned i; - if (ctx->file_data) + if (ctx->file_table.data.nr) return -EBUSY; if (!nr_args) return -EINVAL; @@ -543,17 +511,10 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return -EMFILE; if (nr_args > rlimit(RLIMIT_NOFILE)) return -EMFILE; - ret = io_rsrc_data_alloc(ctx, nr_args, &ctx->file_data); - if (ret) - return ret; - - if (!io_alloc_file_tables(&ctx->file_table, nr_args)) { - io_rsrc_data_free(ctx->file_data); - ctx->file_data = NULL; + if (!io_alloc_file_tables(&ctx->file_table, nr_args)) return -ENOMEM; - } - for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { + for (i = 0; i < nr_args; i++) { struct io_rsrc_node *node; u64 tag = 0; @@ -583,51 +544,32 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, goto fail; } ret = -ENOMEM; - node = io_rsrc_node_alloc(ctx, ctx->file_data, IORING_RSRC_FILE); + node = io_rsrc_node_alloc(ctx, &ctx->file_table.data, + IORING_RSRC_FILE); if (!node) { fput(file); goto fail; } if (tag) node->tag = tag; - ctx->file_table.nodes[i] = node; + ctx->file_table.data.nodes[i] = node; io_fixed_file_set(node, file); io_file_bitmap_set(&ctx->file_table, i); } /* default it to the whole table */ - io_file_table_set_alloc_range(ctx, 0, ctx->nr_user_files); + io_file_table_set_alloc_range(ctx, 0, ctx->file_table.data.nr); return 0; fail: - __io_sqe_files_unregister(ctx); + io_sqe_files_unregister(ctx); return ret; } -static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx) -{ - unsigned int i; - - lockdep_assert_held(&ctx->uring_lock); - - for (i = 0; i < ctx->nr_user_bufs; i++) { - if (ctx->user_bufs[i]) { - io_put_rsrc_node(ctx->user_bufs[i]); - ctx->user_bufs[i] = NULL; - } - } - kvfree(ctx->user_bufs); - ctx->user_bufs = NULL; - io_rsrc_data_free(ctx->buf_data); - ctx->buf_data = NULL; - ctx->nr_user_bufs = 0; -} - int io_sqe_buffers_unregister(struct io_ring_ctx *ctx) { - if (!ctx->buf_data) + if (!ctx->buf_table.nr) return -ENXIO; - - __io_sqe_buffers_unregister(ctx); + io_rsrc_data_free(&ctx->buf_table); return 0; } @@ -654,8 +596,8 @@ static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages, } /* check previously registered pages */ - for (i = 0; i < ctx->nr_user_bufs; i++) { - struct io_rsrc_node *node = ctx->user_bufs[i]; + for (i = 0; i < ctx->buf_table.nr; i++) { + struct io_rsrc_node *node = ctx->buf_table.nodes[i]; struct io_mapped_ubuf *imu = node->buf; for (j = 0; j < imu->nr_bvecs; j++) { @@ -807,7 +749,10 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, struct io_imu_folio_data data; bool coalesced; - node = io_rsrc_node_alloc(ctx, ctx->buf_data, IORING_RSRC_BUFFER); + if (!iov->iov_base) + return rsrc_empty_node; + + node = io_rsrc_node_alloc(ctx, &ctx->buf_table, IORING_RSRC_BUFFER); if (!node) return ERR_PTR(-ENOMEM); @@ -865,40 +810,29 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, return node; } -static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args) -{ - ctx->user_bufs = kcalloc(nr_args, sizeof(*ctx->user_bufs), GFP_KERNEL); - return ctx->user_bufs ? 0 : -ENOMEM; -} - int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, unsigned int nr_args, u64 __user *tags) { struct page *last_hpage = NULL; - struct io_rsrc_data *data; + struct io_rsrc_data data; struct iovec fast_iov, *iov = &fast_iov; const struct iovec __user *uvec; int i, ret; BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16)); - if (ctx->user_bufs) + if (ctx->buf_table.nr) return -EBUSY; if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS) return -EINVAL; - ret = io_rsrc_data_alloc(ctx, nr_args, &data); + ret = io_rsrc_data_alloc(&data, nr_args); if (ret) return ret; - ret = io_buffers_map_alloc(ctx, nr_args); - if (ret) { - io_rsrc_data_free(data); - return ret; - } if (!arg) memset(iov, 0, sizeof(*iov)); - for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) { + for (i = 0; i < nr_args; i++) { struct io_rsrc_node *node; u64 tag = 0; @@ -936,14 +870,12 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, } if (tag) node->tag = tag; - ctx->user_bufs[i] = node; + data.nodes[i] = node; } - WARN_ON_ONCE(ctx->buf_data); - - ctx->buf_data = data; + ctx->buf_table = data; if (ret) - __io_sqe_buffers_unregister(ctx); + io_sqe_buffers_unregister(ctx); return ret; } @@ -1010,8 +942,7 @@ int io_import_fixed(int ddir, struct iov_iter *iter, static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx) { - struct io_rsrc_node **user_bufs; - struct io_rsrc_data *data; + struct io_rsrc_data data; int i, ret, nbufs; /* @@ -1022,43 +953,35 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx mutex_lock(&src_ctx->uring_lock); ret = -ENXIO; - nbufs = src_ctx->nr_user_bufs; + nbufs = src_ctx->buf_table.nr; if (!nbufs) goto out_unlock; - ret = io_rsrc_data_alloc(ctx, nbufs, &data); + ret = io_rsrc_data_alloc(&data, nbufs); if (ret) goto out_unlock; - ret = -ENOMEM; - user_bufs = kvmalloc_array(nbufs, sizeof(struct io_rsrc_node *), - GFP_KERNEL | __GFP_ZERO); - if (!user_bufs) - goto out_free_data; - for (i = 0; i < nbufs; i++) { - struct io_rsrc_node *src_node = src_ctx->user_bufs[i]; + struct io_rsrc_node *src_node = src_ctx->buf_table.nodes[i]; struct io_rsrc_node *dst_node; if (src_node == rsrc_empty_node) { dst_node = rsrc_empty_node; } else { - dst_node = io_rsrc_node_alloc(ctx, data, IORING_RSRC_BUFFER); + dst_node = io_rsrc_node_alloc(ctx, &data, IORING_RSRC_BUFFER); if (!dst_node) goto out_put_free; refcount_inc(&src_node->buf->refs); dst_node->buf = src_node->buf; } - user_bufs[i] = dst_node; + data.nodes[i] = dst_node; } /* Have a ref on the bufs now, drop src lock and re-grab our own lock */ mutex_unlock(&src_ctx->uring_lock); mutex_lock(&ctx->uring_lock); - if (!ctx->user_bufs) { - ctx->user_bufs = user_bufs; - ctx->buf_data = data; - ctx->nr_user_bufs = nbufs; + if (!ctx->buf_table.nr) { + ctx->buf_table = data; return 0; } @@ -1069,12 +992,10 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx i = nbufs; out_put_free: while (i--) { - io_buffer_unmap(src_ctx, user_bufs[i]); - kfree(user_bufs[i]); + io_buffer_unmap(src_ctx, data.nodes[i]); + kfree(data.nodes[i]); } - kvfree(user_bufs); -out_free_data: - io_rsrc_data_free(data); + io_rsrc_data_free(&data); out_unlock: mutex_unlock(&src_ctx->uring_lock); mutex_lock(&ctx->uring_lock); @@ -1095,7 +1016,7 @@ int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg) struct file *file; int ret; - if (ctx->user_bufs || ctx->nr_user_bufs) + if (ctx->buf_table.nr) return -EBUSY; if (copy_from_user(&buf, arg, sizeof(buf))) return -EFAULT; diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 6a7863f13ea9..438e0ac6abf7 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -13,11 +13,6 @@ enum { IORING_RSRC_BUFFER = 1, }; -struct io_rsrc_data { - unsigned int nr; - struct io_rsrc_node **nodes; -}; - struct io_rsrc_node { struct io_ring_ctx *ctx; int refs; @@ -51,6 +46,8 @@ struct io_imu_folio_data { struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, struct io_rsrc_data *data, int type); void io_free_rsrc_node(struct io_rsrc_node *node); +void io_rsrc_data_free(struct io_rsrc_data *data); +int io_rsrc_data_alloc(struct io_rsrc_data *data, unsigned nr); int io_import_fixed(int ddir, struct iov_iter *iter, struct io_mapped_ubuf *imu, diff --git a/io_uring/rw.c b/io_uring/rw.c index 65491f4f2c7e..28fff18ebb19 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -339,10 +339,10 @@ static int io_prep_rw_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe if (unlikely(ret)) return ret; - if (unlikely(req->buf_index >= ctx->nr_user_bufs)) + if (unlikely(req->buf_index >= ctx->buf_table.nr)) return -EFAULT; - index = array_index_nospec(req->buf_index, ctx->nr_user_bufs); - node = ctx->user_bufs[index]; + index = array_index_nospec(req->buf_index, ctx->buf_table.nr); + node = ctx->buf_table.nodes[index]; io_req_assign_rsrc_node(req, node); io = req->async_data; diff --git a/io_uring/splice.c b/io_uring/splice.c index f78afb575ae6..aaaddb66e90a 100644 --- a/io_uring/splice.c +++ b/io_uring/splice.c @@ -66,10 +66,10 @@ static struct file *io_splice_get_file(struct io_kiocb *req, return io_file_get_normal(req, sp->splice_fd_in); io_ring_submit_lock(ctx, issue_flags); - if (unlikely(sp->splice_fd_in >= ctx->nr_user_files)) + if (unlikely(sp->splice_fd_in >= ctx->file_table.data.nr)) goto out; - sp->splice_fd_in = array_index_nospec(sp->splice_fd_in, ctx->nr_user_files); - node = ctx->file_table.nodes[sp->splice_fd_in]; + sp->splice_fd_in = array_index_nospec(sp->splice_fd_in, ctx->file_table.data.nr); + node = ctx->file_table.data.nodes[sp->splice_fd_in]; if (node) { node->refs++; sp->rsrc_node = node; diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 0899c71008ae..17d5f5004702 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -212,15 +212,15 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) u16 index; index = READ_ONCE(sqe->buf_index); - if (unlikely(index >= ctx->nr_user_bufs)) + if (unlikely(index >= ctx->buf_table.nr)) return -EFAULT; - req->buf_index = array_index_nospec(index, ctx->nr_user_bufs); + req->buf_index = array_index_nospec(index, ctx->buf_table.nr); /* * Pi node upfront, prior to io_uring_cmd_import_fixed() * being called. This prevents destruction of the mapped buffer * we'll need at actual import time. */ - io_req_assign_rsrc_node(req, ctx->user_bufs[req->buf_index]); + io_req_assign_rsrc_node(req, ctx->buf_table.nodes[req->buf_index]); } ioucmd->cmd_op = READ_ONCE(sqe->cmd_op); From patchwork Tue Oct 29 15:16:40 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855095 Received: from mail-io1-f53.google.com (mail-io1-f53.google.com [209.85.166.53]) (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 A7DC5194A64 for ; Tue, 29 Oct 2024 15:23:17 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.53 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215400; cv=none; b=g74zfAcsfUONi8Qnsr78RY2Iaer5/ZSMjWN9upAc6KGjh+DRF8w8VuqsShEwUT3ztC80HGuHMPjJ+aJGFUASVFiOBNv0yuxjL/CRXcu2qWrpoDZIPf/Sq5ky1yY3RmOnfo9gc5yBiplpojIi+SoPlP/Jv0OoAzdcHgse25knSvQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215400; c=relaxed/simple; bh=xlqUmmAAAFdpSt0oI3cj/qRICnW+M5T/Lr9Gngjg2wQ=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=NRWJYyVGXzcoeH7VzO3WBHC4R3agf+GxBoskJIV7wAfrjq7BmZhG8gwJnNuYC/VWtIRfxZCg93bpbUgkGg8WcAEOWA//5a8eU4u4lE1pMcP4hNFh9HAe+Ks9ZUnb0gu3PEY0+72UW5Wbv0QOcSLgkKuwo/q4mIVI5/0VMLSop6Y= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=Ci2DUGfM; arc=none smtp.client-ip=209.85.166.53 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="Ci2DUGfM" Received: by mail-io1-f53.google.com with SMTP id ca18e2360f4ac-83a9be2c0e6so212164539f.2 for ; Tue, 29 Oct 2024 08:23:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215396; x=1730820196; darn=vger.kernel.org; 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=ygh/OC1xh/vCMWKCfVOfQzTNBpIeWGRvL/JRac4VemA=; b=Ci2DUGfM/xcCZLxWEUrp1p3vIol9HT3jwR0uarKuaWNs7ignHsKZZUCLrQljiwFxlp QCSa+cRkrJ769y5WCqcGM6D3FOI8Q9IaeeARje9vebpibb6pdCLezRWsdfhp0ozO1S6y 5dozztN2XoN2wg83gIjUYgk+++eblt2fDKeKicQkjGduNFjVJwOjK9SdvHD/yJNL9kdw UnOun3zzxR+ETMq/ZtXDa9QLxhHwHzj/vuUUXabrJmKTiUzb9dSt5J7U1DXIcZdnX2rV 5r9Gf1K/pl059Yk+Azgpx4e5EEoejMQZ2z2fxjfUokdEMHHTgfbQF8DwtCUOOpMcw15X xZFA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215396; x=1730820196; 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=ygh/OC1xh/vCMWKCfVOfQzTNBpIeWGRvL/JRac4VemA=; b=RzU1tOHFKQbiM5BAh1Jy55uZ0L/+6jqwWaco7qUgmHtHDKjy2VB/jnkhwvaQJqV0TS XzDBe6oOvo8r0NQtR7iiyt1saXByAKDWB6dMuJVrmyfgDuZSVjelzPXjMEhRoKX+CGnn wZG22y7VtxHnoSO+jWeHrwfI+h+9Zad08hYOpesouHTutqTMCo3LRy7BrGrW1XNIVFyQ 7cXVVcRU3RdmD0dqG5L/jN16lqF+Euq7v1cNVVoPrnvy+Oy8hRhX3LEMnsGMMtkmNMWM aKNgVjmNnuHWccd3toG1urzQNXwtwwU6TdsGX2bXfr+QfC/YT2drQlaC122c/qQGmlWF /rww== X-Gm-Message-State: AOJu0Yw8AzCeo6BWL9FKr16XrT+zFvdMk86gfkR5ssM0Qmgc91YERaE3 QtntzHLquoZIhrF1jwGFZ9y8z1OvrmMKXGfxKwwAeN0pKmwYaKAMiyXOrFRTaNozOnyzKpSndwD s X-Google-Smtp-Source: AGHT+IF/g3S0z7eXN99M4rGt55k1nDf9+w0tJT/rb0/zEvTalFyF2UVE/rkWS6q9hpwSY3ufdrwMQw== X-Received: by 2002:a05:6602:6002:b0:83a:a96b:8825 with SMTP id ca18e2360f4ac-83b1bcefdebmr1251718539f.0.1730215396254; Tue, 29 Oct 2024 08:23:16 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.15 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:15 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 11/14] io_uring/rsrc: add io_rsrc_node_lookup() helper Date: Tue, 29 Oct 2024 09:16:40 -0600 Message-ID: <20241029152249.667290-12-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 There are lots of spots open-coding this functionality, add a generic helper that does the node lookup in a speculation safe way. Signed-off-by: Jens Axboe --- io_uring/cancel.c | 8 +++++--- io_uring/filetable.c | 16 +++++++++------- io_uring/filetable.h | 2 +- io_uring/io_uring.c | 6 +----- io_uring/msg_ring.c | 31 +++++++++++++++---------------- io_uring/net.c | 6 ++---- io_uring/nop.c | 6 ++---- io_uring/rsrc.c | 12 +++++++----- io_uring/rsrc.h | 8 ++++++++ io_uring/rw.c | 6 ++---- io_uring/splice.c | 6 +----- io_uring/uring_cmd.c | 9 ++++----- 12 files changed, 57 insertions(+), 59 deletions(-) diff --git a/io_uring/cancel.c b/io_uring/cancel.c index 3a2996307025..bbca5cb69cb5 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -240,10 +240,12 @@ static int __io_sync_cancel(struct io_uring_task *tctx, /* fixed must be grabbed every time since we drop the uring_lock */ if ((cd->flags & IORING_ASYNC_CANCEL_FD) && (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) { - if (unlikely(fd >= ctx->file_table.data.nr)) + struct io_rsrc_node *node; + + node = io_rsrc_node_lookup(&ctx->file_table.data, fd); + if (unlikely(!node)) return -EBADF; - fd = array_index_nospec(fd, ctx->file_table.data.nr); - cd->file = io_file_from_index(&ctx->file_table, fd); + cd->file = io_slot_file(node); if (!cd->file) return -EBADF; } diff --git a/io_uring/filetable.c b/io_uring/filetable.c index c1bea2d9dce2..1f22f183cdeb 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -58,7 +58,7 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, u32 slot_index) __must_hold(&req->ctx->uring_lock) { - struct io_rsrc_node *node; + struct io_rsrc_node *node, *old_node; if (io_is_uring_fops(file)) return -EBADF; @@ -71,9 +71,9 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, if (IS_ERR(node)) return -ENOMEM; - slot_index = array_index_nospec(slot_index, ctx->file_table.data.nr); - if (ctx->file_table.data.nodes[slot_index]) - io_put_rsrc_node(ctx->file_table.data.nodes[slot_index]); + old_node = io_rsrc_node_lookup(&ctx->file_table.data, slot_index); + if (old_node) + io_put_rsrc_node(old_node); else io_file_bitmap_set(&ctx->file_table, slot_index); @@ -123,15 +123,17 @@ int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags, int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset) { + struct io_rsrc_node *node; + if (unlikely(!ctx->file_table.data.nr)) return -ENXIO; if (offset >= ctx->file_table.data.nr) return -EINVAL; - offset = array_index_nospec(offset, ctx->file_table.data.nr); - if (!ctx->file_table.data.nodes[offset]) + node = io_rsrc_node_lookup(&ctx->file_table.data, offset); + if (!node) return -EBADF; - io_put_rsrc_node(ctx->file_table.data.nodes[offset]); + io_put_rsrc_node(node); ctx->file_table.data.nodes[offset] = NULL; io_file_bitmap_clear(&ctx->file_table, offset); return 0; diff --git a/io_uring/filetable.h b/io_uring/filetable.h index 664c31502dbb..29edda0caa65 100644 --- a/io_uring/filetable.h +++ b/io_uring/filetable.h @@ -52,7 +52,7 @@ static inline struct file *io_slot_file(struct io_rsrc_node *node) static inline struct file *io_file_from_index(struct io_file_table *table, int index) { - struct io_rsrc_node *node = table->data.nodes[index]; + struct io_rsrc_node *node = io_rsrc_node_lookup(&table->data, index); if (node) return io_slot_file(node); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 78df515fb3a7..3a535e9e8ac3 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1879,16 +1879,12 @@ inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, struct file *file = NULL; io_ring_submit_lock(ctx, issue_flags); - if (unlikely((unsigned int)fd >= ctx->file_table.data.nr)) - goto out; - fd = array_index_nospec(fd, ctx->file_table.data.nr); - node = ctx->file_table.data.nodes[fd]; + node = io_rsrc_node_lookup(&ctx->file_table.data, fd); if (node) { io_req_assign_rsrc_node(req, node); req->flags |= io_slot_flags(node); file = io_slot_file(node); } -out: io_ring_submit_unlock(ctx, issue_flags); return file; } diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index b90ab3b8f5e0..99af39e1d0fb 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -172,22 +172,24 @@ static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags) return __io_msg_ring_data(target_ctx, msg, issue_flags); } -static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags) +static int io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags) { struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); struct io_ring_ctx *ctx = req->ctx; - struct file *file = NULL; - int idx = msg->src_fd; + struct io_rsrc_node *node; + int ret = -EBADF; io_ring_submit_lock(ctx, issue_flags); - if (likely(idx < ctx->file_table.data.nr)) { - idx = array_index_nospec(idx, ctx->file_table.data.nr); - file = io_file_from_index(&ctx->file_table, idx); - if (file) - get_file(file); + node = io_rsrc_node_lookup(&ctx->file_table.data, msg->src_fd); + if (node) { + msg->src_file = io_slot_file(node); + if (msg->src_file) + get_file(msg->src_file); + req->flags |= REQ_F_NEED_CLEANUP; + ret = 0; } io_ring_submit_unlock(ctx, issue_flags); - return file; + return ret; } static int io_msg_install_complete(struct io_kiocb *req, unsigned int issue_flags) @@ -256,7 +258,6 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) struct io_ring_ctx *target_ctx = req->file->private_data; struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); struct io_ring_ctx *ctx = req->ctx; - struct file *src_file = msg->src_file; if (msg->len) return -EINVAL; @@ -264,12 +265,10 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) return -EINVAL; if (target_ctx->flags & IORING_SETUP_R_DISABLED) return -EBADFD; - if (!src_file) { - src_file = io_msg_grab_file(req, issue_flags); - if (!src_file) - return -EBADF; - msg->src_file = src_file; - req->flags |= REQ_F_NEED_CLEANUP; + if (!msg->src_file) { + int ret = io_msg_grab_file(req, issue_flags); + if (unlikely(ret)) + return ret; } if (io_msg_need_remote(target_ctx)) diff --git a/io_uring/net.c b/io_uring/net.c index 3e1f31574abb..2f7b334ed708 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1343,13 +1343,11 @@ static int io_send_zc_import(struct io_kiocb *req, unsigned int issue_flags) if (sr->flags & IORING_RECVSEND_FIXED_BUF) { struct io_ring_ctx *ctx = req->ctx; struct io_rsrc_node *node; - int idx; ret = -EFAULT; io_ring_submit_lock(ctx, issue_flags); - if (sr->buf_index < ctx->buf_table.nr) { - idx = array_index_nospec(sr->buf_index, ctx->buf_table.nr); - node = ctx->buf_table.nodes[idx]; + node = io_rsrc_node_lookup(&ctx->buf_table, sr->buf_index); + if (node) { io_req_assign_rsrc_node(sr->notif, node); ret = 0; } diff --git a/io_uring/nop.c b/io_uring/nop.c index 0dac01127de5..149dbdc53607 100644 --- a/io_uring/nop.c +++ b/io_uring/nop.c @@ -62,13 +62,11 @@ int io_nop(struct io_kiocb *req, unsigned int issue_flags) if (nop->flags & IORING_NOP_FIXED_BUFFER) { struct io_ring_ctx *ctx = req->ctx; struct io_rsrc_node *node; - int idx; ret = -EFAULT; io_ring_submit_lock(ctx, issue_flags); - if (nop->buffer < ctx->buf_table.nr) { - idx = array_index_nospec(nop->buffer, ctx->buf_table.nr); - node = READ_ONCE(ctx->buf_table.nodes[idx]); + node = io_rsrc_node_lookup(&ctx->buf_table, nop->buffer); + if (node) { io_req_assign_rsrc_node(req, node); ret = 0; } diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 902e003704a9..0924c53dd954 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -182,6 +182,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, return -EINVAL; for (done = 0; done < nr_args; done++) { + struct io_rsrc_node *node; u64 tag = 0; if ((tags && copy_from_user(&tag, &tags[done], sizeof(tag))) || @@ -196,9 +197,10 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (fd == IORING_REGISTER_FILES_SKIP) continue; - i = array_index_nospec(up->offset + done, ctx->file_table.data.nr); - if (ctx->file_table.data.nodes[i]) { - io_put_rsrc_node(ctx->file_table.data.nodes[i]); + i = up->offset + done; + node = io_rsrc_node_lookup(&ctx->file_table.data, i); + if (node) { + io_put_rsrc_node(node); ctx->file_table.data.nodes[i] = NULL; io_file_bitmap_clear(&ctx->file_table, i); } @@ -961,9 +963,9 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx goto out_unlock; for (i = 0; i < nbufs; i++) { - struct io_rsrc_node *src_node = src_ctx->buf_table.nodes[i]; - struct io_rsrc_node *dst_node; + struct io_rsrc_node *dst_node, *src_node; + src_node = io_rsrc_node_lookup(&src_ctx->buf_table, i); if (src_node == rsrc_empty_node) { dst_node = rsrc_empty_node; } else { diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 438e0ac6abf7..6952fb45f57a 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -71,6 +71,14 @@ int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, extern const struct io_rsrc_node empty_node; #define rsrc_empty_node (struct io_rsrc_node *) &empty_node +static inline struct io_rsrc_node *io_rsrc_node_lookup(struct io_rsrc_data *data, + int index) +{ + if (index < data->nr) + return data->nodes[array_index_nospec(index, data->nr)]; + return NULL; +} + static inline void io_put_rsrc_node(struct io_rsrc_node *node) { if (node != rsrc_empty_node && !--node->refs) diff --git a/io_uring/rw.c b/io_uring/rw.c index 28fff18ebb19..30448f343c7f 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -332,17 +332,15 @@ static int io_prep_rw_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe struct io_ring_ctx *ctx = req->ctx; struct io_rsrc_node *node; struct io_async_rw *io; - u16 index; int ret; ret = io_prep_rw(req, sqe, ddir, false); if (unlikely(ret)) return ret; - if (unlikely(req->buf_index >= ctx->buf_table.nr)) + node = io_rsrc_node_lookup(&ctx->buf_table, req->buf_index); + if (!node) return -EFAULT; - index = array_index_nospec(req->buf_index, ctx->buf_table.nr); - node = ctx->buf_table.nodes[index]; io_req_assign_rsrc_node(req, node); io = req->async_data; diff --git a/io_uring/splice.c b/io_uring/splice.c index aaaddb66e90a..deeb8bb18651 100644 --- a/io_uring/splice.c +++ b/io_uring/splice.c @@ -66,17 +66,13 @@ static struct file *io_splice_get_file(struct io_kiocb *req, return io_file_get_normal(req, sp->splice_fd_in); io_ring_submit_lock(ctx, issue_flags); - if (unlikely(sp->splice_fd_in >= ctx->file_table.data.nr)) - goto out; - sp->splice_fd_in = array_index_nospec(sp->splice_fd_in, ctx->file_table.data.nr); - node = ctx->file_table.data.nodes[sp->splice_fd_in]; + node = io_rsrc_node_lookup(&ctx->file_table.data, sp->splice_fd_in); if (node) { node->refs++; sp->rsrc_node = node; file = io_slot_file(node); req->flags |= REQ_F_NEED_CLEANUP; } -out: io_ring_submit_unlock(ctx, issue_flags); return file; } diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 17d5f5004702..535909a38e76 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -209,18 +209,17 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (ioucmd->flags & IORING_URING_CMD_FIXED) { struct io_ring_ctx *ctx = req->ctx; - u16 index; + struct io_rsrc_node *node; - index = READ_ONCE(sqe->buf_index); - if (unlikely(index >= ctx->buf_table.nr)) + node = io_rsrc_node_lookup(&ctx->buf_table, req->buf_index); + if (unlikely(!node)) return -EFAULT; - req->buf_index = array_index_nospec(index, ctx->buf_table.nr); /* * Pi node upfront, prior to io_uring_cmd_import_fixed() * being called. This prevents destruction of the mapped buffer * we'll need at actual import time. */ - io_req_assign_rsrc_node(req, ctx->buf_table.nodes[req->buf_index]); + io_req_assign_rsrc_node(req, node); } ioucmd->cmd_op = READ_ONCE(sqe->cmd_op); From patchwork Tue Oct 29 15:16:41 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855096 Received: from mail-io1-f50.google.com (mail-io1-f50.google.com [209.85.166.50]) (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 AF97B192B77 for ; Tue, 29 Oct 2024 15:23:18 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.50 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215401; cv=none; b=na5uP/I0T59bkdwfpBn3Y8j9JsG6egr2pLy0Fwv70KeDIj0yCDndmD1Lky393fXgf15gsHf+R2SsqlB9zm8wHDlZZLQIZ7/wMRZRrAt9GgusDOJHDx3Z0jlwvm3xFIZdtCTIMHE5Q2lH3wY8cvdBTstm6JdJ1IVdhMDhp/L+778= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215401; c=relaxed/simple; bh=29WfLfchpB31ecsDmbLXfbvXZ6Z5zdmNqGCC0eIaSj0=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=H1x7smR8LfG4Qh3GvR7o5BIg45f2s6xVtqeJgvZyCH2nPBrdFjYAIwCs2+sTCKil6xxvzv5LHDj8YaBn7356gTubF0M6wr4jX5Q//FpuYbwbQ8TMUV4gTUk0j+mTA9eBwPZsYBZeQuLXc5FGu4BM6SL6vCnjLU4uciYZdS4PSEU= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=111bQjNn; arc=none smtp.client-ip=209.85.166.50 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="111bQjNn" Received: by mail-io1-f50.google.com with SMTP id ca18e2360f4ac-83a9be2c028so207848239f.1 for ; Tue, 29 Oct 2024 08:23:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215397; x=1730820197; darn=vger.kernel.org; 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=/iw1ID0xXFiXgPx+FCcIfK0kokYS+rNNPARBrPnOuXs=; b=111bQjNnuixFZrca7czsu8UeuuH4m+apqfYKfCcIysN86B1AS6enMt4SDusP9VxV3V qjGVhpg6tgmPW9zGBUMUbNXpNaE7QV88dA8GriIcBZ80dWFsCgUsLZH1vt4iXY3gbWdj 0pa5Hiskmdx8aUzjee1yS9XlKENM4CICpwG+eYPrvErB9lX0y6lYN0HAe0aSvhHqB6rT QUHIQacI3PngXxL1oK7hIrJZhK7BbhLvMZ/tQXS+PikU6RMIqIh/3N9RrhBkR9uicH+H vG0zTameYipzOE41MTFcq3mpgKGqQ51B+VcICoMOEps394agqetndVMzNaXxQD5oVQe7 CFBA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215397; x=1730820197; 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=/iw1ID0xXFiXgPx+FCcIfK0kokYS+rNNPARBrPnOuXs=; b=ZmoZcRnYFRZZBnQbzdzOjKPrmH1cGWoMXbyWt/2pBOVpkRPHe5UHkfJS0xVFT92HIa SfR+n9rUvvVtcunp+Xg1AiAdMEeggEcBL+pPm5LkqMReVq/QpdogLeLn1gHechsQ8fuK HuULj7Gf6sYxdW3/SV1Uiayl+oZI7hgH7Sgl/22lVGAaBMugek4N270QPHFQU5Z54vkb buOWeB5nKwetNUO7JTCvXU6e9dua45YRqVGo9MgE3m3coBI8X0iPZEE/egllu3kj4Zha /ZwmAkasCsQsA0qtgMCoohJfVQH/HauQtfTnYI/Ar41ziyPg6CAARrVq0uViWZp3ghXe VuYQ== X-Gm-Message-State: AOJu0YzhVyAypXk+ORb9+/YcfPBTSGEBVhXhSwMPIYe9hc/c/kzUO4N4 5xXVVghNqu0+bAJGVgEGJ1nNPXb+8kNuXv7p3HaQrSlkTKHSDMT7vUcLpsXYE5FHj8QLXirO2ID Q X-Google-Smtp-Source: AGHT+IGYTzDxxJwQwC+RBGI8hM+oO5HDBIX1rvhOQFCKWfAYOC+KBWaW2+/fbu7HO2fw+2h+qbGldw== X-Received: by 2002:a05:6602:2b01:b0:83a:b7e8:a684 with SMTP id ca18e2360f4ac-83b1c60b7d9mr1461007939f.11.1730215397502; Tue, 29 Oct 2024 08:23:17 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.16 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:16 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 12/14] io_uring/filetable: remove io_file_from_index() helper Date: Tue, 29 Oct 2024 09:16:41 -0600 Message-ID: <20241029152249.667290-13-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 It's only used in fdinfo, nothing really gained from having this helper. Signed-off-by: Jens Axboe --- io_uring/fdinfo.c | 4 +++- io_uring/filetable.h | 10 ---------- 2 files changed, 3 insertions(+), 11 deletions(-) diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index e3f5e9fe5562..9d96481e2eb6 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -167,8 +167,10 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time); seq_printf(m, "UserFiles:\t%u\n", ctx->file_table.data.nr); for (i = 0; has_lock && i < ctx->file_table.data.nr; i++) { - struct file *f = io_file_from_index(&ctx->file_table, i); + struct file *f = NULL; + if (ctx->file_table.data.nodes[i]) + f = io_slot_file(ctx->file_table.data.nodes[i]); if (f) seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname); else diff --git a/io_uring/filetable.h b/io_uring/filetable.h index 29edda0caa65..6c0c9642f6e9 100644 --- a/io_uring/filetable.h +++ b/io_uring/filetable.h @@ -49,16 +49,6 @@ static inline struct file *io_slot_file(struct io_rsrc_node *node) return (struct file *)(node->file_ptr & FFS_MASK); } -static inline struct file *io_file_from_index(struct io_file_table *table, - int index) -{ - struct io_rsrc_node *node = io_rsrc_node_lookup(&table->data, index); - - if (node) - return io_slot_file(node); - return NULL; -} - static inline void io_fixed_file_set(struct io_rsrc_node *node, struct file *file) { From patchwork Tue Oct 29 15:16:42 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855097 Received: from mail-io1-f47.google.com (mail-io1-f47.google.com [209.85.166.47]) (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 2677C193416 for ; Tue, 29 Oct 2024 15:23:19 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.47 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215402; cv=none; b=Dn/Ug6vJRpB6vIFy7xkNiSIvrSo8sFP3mMLHH7BM55EElLFPN2J2CC4OTuNBUxTvw8o4dgYC7yAJVGJ92VqziUQwdJA9lLTxd1GnvxeA1gy9iRab70zHs5Gvia9+5lx4q7xIx7uyLqZr+hWEw0DAuWEio9DqKfLmTC7zDUnXO6w= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215402; c=relaxed/simple; bh=ZtTuIg71Y7d8GwNOGFMCoLgePIhoo4ujtF6+yd5PsPw=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=O3pjqkeWyr/s6vsts1M/vLLbF/If8l7ZovPwTmuQoi7w4IAJKqAF0nYhm6oX48EvB+mRe3MzXWblN/ktuNb88/XlGLED0Wk4wrFEm6jSdNyX+j5ETHRVA9Yo5sDIl4dDyjwvbtPPN1wu99MsTKQxj5aoVet9YotYC+eZMGIZeo4= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=Dkrplgux; arc=none smtp.client-ip=209.85.166.47 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="Dkrplgux" Received: by mail-io1-f47.google.com with SMTP id ca18e2360f4ac-83b2a41b81cso101780539f.0 for ; Tue, 29 Oct 2024 08:23:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215399; x=1730820199; darn=vger.kernel.org; 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=WTbLEVTHcZTbfKmFj6UiMSsh5E/ApXC9ukCVRFjC63Q=; b=DkrplguxRVYaUig1hoxKmJzNHwzguw9NomcwnIFUe8MM7JFgpQC9kSE7BKeqiPE1eJ 7sep4G/Kq9YdEfwSqLOqqPts7nWeiwWm/9OA4axouDMfyA+SISCHpBRSkVeFGdiW1O25 0i7s29fIpdefyRMN/3gD6tAe/xZTbL2alwFPNmx5oYGmibst+C166dsou/nwu1+3siJe e59T3Z0MY00XKgI3yViWW3SiniuyHJpXB2I615+5dBiBqlWhO63hZVkt0jS8xl0a0+ao PDDtozVqoAojqQZg3M+dXSGlCSqmGPBw5M/hjwt6j007eFb9s+tjMfIb5hGoH1Q4N7nW ZOlQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215399; x=1730820199; 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=WTbLEVTHcZTbfKmFj6UiMSsh5E/ApXC9ukCVRFjC63Q=; b=TVnzK2tmeMSfneefJSEP+evVLcEjQHgJCVYd2pBa8iblgGHxaGmBS8Gl5Tqs4j4dGQ 4fejAfeVkfRb7VYEOq9OvxRCoJ+lM/c2y8qdkGDgnTC9XrTYQoUHwtbD7k9GDZwrm9DD qWqv87H7vRsSscZ/gngbrRSX5Bvc3H7o08Q+nn4mS0GUVMmaTg+Gr50m2ZK4myWkMx6j mF6WHr3z4azsm463Fhx3AoOMtycL5Vqlj0gg3zsHdWnlnkHZ0CSQ7/1BVIjUsAvCtFV3 J8C1cccC4JPhQWcImCRQgHHnXDmZNvT0S9i2yPq28tg9d6uWciBOTHretqwdy40+Doge KtXA== X-Gm-Message-State: AOJu0Yz5MYmr1qvRqgaDVMJJ+/PkgK2GgzP97uoX+AW5wuWpMW2fNaLt nN3OMpNICwrJx1cfVN4hNMXMFK2ePlBxPmDhW+B6QGGJ8YYkfDHnqMH18GFfyE/B98CV5Ipa0Q3 9 X-Google-Smtp-Source: AGHT+IEe5u7WfULkU+qVLJEGXkTsMp5YSCG5GpvZXW7QtCtANmWlhFW7Nc8YGhFBnndRhyRnAX5QnA== X-Received: by 2002:a05:6602:1493:b0:83a:b8aa:ec0 with SMTP id ca18e2360f4ac-83b1c627e42mr1070584039f.13.1730215398836; Tue, 29 Oct 2024 08:23:18 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.17 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:17 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 13/14] io_uring/filetable: kill io_reset_alloc_hint() helper Date: Tue, 29 Oct 2024 09:16:42 -0600 Message-ID: <20241029152249.667290-14-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 It's only used internally, and in one spot, just open-code ti. Signed-off-by: Jens Axboe --- io_uring/filetable.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/io_uring/filetable.h b/io_uring/filetable.h index 6c0c9642f6e9..bfacadb8d089 100644 --- a/io_uring/filetable.h +++ b/io_uring/filetable.h @@ -56,17 +56,12 @@ static inline void io_fixed_file_set(struct io_rsrc_node *node, (io_file_get_flags(file) >> REQ_F_SUPPORT_NOWAIT_BIT); } -static inline void io_reset_alloc_hint(struct io_ring_ctx *ctx) -{ - ctx->file_table.alloc_hint = ctx->file_alloc_start; -} - static inline void io_file_table_set_alloc_range(struct io_ring_ctx *ctx, unsigned off, unsigned len) { ctx->file_alloc_start = off; ctx->file_alloc_end = off + len; - io_reset_alloc_hint(ctx); + ctx->file_table.alloc_hint = ctx->file_alloc_start; } #endif From patchwork Tue Oct 29 15:16:43 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 13855099 Received: from mail-io1-f47.google.com (mail-io1-f47.google.com [209.85.166.47]) (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 8DC98193074 for ; Tue, 29 Oct 2024 15:23:21 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.166.47 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215403; cv=none; b=QPsdnE7X5iAIPTka2hHOk8qh27r2MrXurBKaPfwlf3jjpHyMSu3i2IRUHijLwHvLTRbO65KBYc8g6nqaDJHc4aKF2YE7YB0NDupbPpQAsmcVdOKvwf+Xw91ffOJyeDUgmiUeoaqCI/ka/inHz1B1ZVraqd5J2Nc6egLIkImF3LU= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730215403; c=relaxed/simple; bh=uQWCLluDMPQNOEiZ8Ul9ExJn/tDb0mVWPhxe1LwxSMw=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=L4gJKizuT3Wxyx6tARROrRJ41bmJQhG34SUN7Jdalu6g8BFDvnGkgUFfvMkSEWZbQt797/HqdzwBfIRrvuhtTv1rTtoClQBxEXvYOE5t3W1C0dJDcdKDiB908HdyrPyPwzrRvEh7/iOr3bUhrrfczXE++8/SuOABHeJViEZGcjA= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk; spf=pass smtp.mailfrom=kernel.dk; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b=S/0lO4ou; arc=none smtp.client-ip=209.85.166.47 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.dk Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20230601.gappssmtp.com header.i=@kernel-dk.20230601.gappssmtp.com header.b="S/0lO4ou" Received: by mail-io1-f47.google.com with SMTP id ca18e2360f4ac-83ab94452a7so234427139f.3 for ; Tue, 29 Oct 2024 08:23:21 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20230601.gappssmtp.com; s=20230601; t=1730215400; x=1730820200; darn=vger.kernel.org; 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=1g4Gm0gSb+oxL2pvGRFmkBIgUYG3z4aBcpjF/hLkUQI=; b=S/0lO4ou7DzzMIZA1R6loNEAasLLmGm5Imp9BJq5jLNtKO1QXSj5U93C7gSTE1mVGw FX2JpsapLfDkgp5KCCH1j7tpYsDpq8w2k+L0fQldxhJ4ygcLWaRX71UXat0JmYTPPfNi u0J6Zqw5VozIq8Ps+JGKfkomusuzIJfRpLmcdbejw50XFJbV1BFN6MOLGRc0QZ2vMkZg pOxNvpVAIezN8SJY4H21HEeKua1DWXIwOk0reVlXttVe2msvbwp04erCIQ00cKEBVgxa c2oe/Pt7RQevSXCk833pbeV3lyKJIWSVIeppRXwP1cIaGujyhvOuEuJi39QYLomsoO3z DGzg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730215400; x=1730820200; 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=1g4Gm0gSb+oxL2pvGRFmkBIgUYG3z4aBcpjF/hLkUQI=; b=JWWrg8KzTTuRbYmZspQQJHsmx5AG4bCCof0ZjHNNr8Rm1aod7SRwtYuxPzPW7DZOjz Hd7X4py91WN25PNiRHGXwNirZUf5lGoBkPIRoabrd92uSIAAWnizx5qHVCkAkm8kuR4B tuBaNMBYqhxKEE/Yb2w36DQz3AeUCXlaju+/6zxpE0hG2iLc1g/QjwZZpy8h1c80QYKe p0Jio2l1R2/NKBtyf9R7ZjulWgREsgNlL2kwW4u4XCrsJTWbyOzAekEwFNzcABuHoorf M200usI4N6ErsIWq6hWhtPRHvfRLwhl6jaWzpqZ/Jgt+cGaAHd7Bs49amsY5H/PWFujA wpiA== X-Gm-Message-State: AOJu0YyVP5HVcgAJAyaydZNPybTIzoC2Bn8lfvCR8HzaPwS+KcMtNNIP S7N1RCGj7x20EunShP9uuxiy3fCAFLNht5c7Y0e5pRrVxPB3QUfKG1fz044vGy167VBgBr0FHUl z X-Google-Smtp-Source: AGHT+IEB4HZr8SpkQXVyD4kbsc5kytkUQ+KqPkVATsUPNbzuigMUz4DhuLB1QG3QwSYuqPjs/pcsfQ== X-Received: by 2002:a05:6602:6411:b0:83a:9a59:f382 with SMTP id ca18e2360f4ac-83b567b996fmr13630139f.16.1730215400262; Tue, 29 Oct 2024 08:23:20 -0700 (PDT) Received: from localhost.localdomain ([96.43.243.2]) by smtp.gmail.com with ESMTPSA id 8926c6da1cb9f-4dc725eb58esm2434160173.27.2024.10.29.08.23.19 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 29 Oct 2024 08:23:19 -0700 (PDT) From: Jens Axboe To: io-uring@vger.kernel.org Cc: Jens Axboe Subject: [PATCH 14/14] io_uring/rsrc: add io_reset_rsrc_node() helper Date: Tue, 29 Oct 2024 09:16:43 -0600 Message-ID: <20241029152249.667290-15-axboe@kernel.dk> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20241029152249.667290-1-axboe@kernel.dk> References: <20241029152249.667290-1-axboe@kernel.dk> Precedence: bulk X-Mailing-List: io-uring@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Puts and reset an existing node in a slot, if one exists. Returns true if a node was there, false if not. This helps cleanup some of the code that does a lookup just to clear an existing node. Signed-off-by: Jens Axboe --- io_uring/filetable.c | 10 +++------- io_uring/rsrc.c | 12 +++--------- io_uring/rsrc.h | 11 +++++++++++ 3 files changed, 17 insertions(+), 16 deletions(-) diff --git a/io_uring/filetable.c b/io_uring/filetable.c index 1f22f183cdeb..717d5b806781 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -58,7 +58,7 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, u32 slot_index) __must_hold(&req->ctx->uring_lock) { - struct io_rsrc_node *node, *old_node; + struct io_rsrc_node *node; if (io_is_uring_fops(file)) return -EBADF; @@ -71,10 +71,7 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, if (IS_ERR(node)) return -ENOMEM; - old_node = io_rsrc_node_lookup(&ctx->file_table.data, slot_index); - if (old_node) - io_put_rsrc_node(old_node); - else + if (!io_reset_rsrc_node(&ctx->file_table.data, slot_index)) io_file_bitmap_set(&ctx->file_table, slot_index); ctx->file_table.data.nodes[slot_index] = node; @@ -133,8 +130,7 @@ int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset) node = io_rsrc_node_lookup(&ctx->file_table.data, offset); if (!node) return -EBADF; - io_put_rsrc_node(node); - ctx->file_table.data.nodes[offset] = NULL; + io_reset_rsrc_node(&ctx->file_table.data, offset); io_file_bitmap_clear(&ctx->file_table, offset); return 0; } diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 0924c53dd954..97673771a0fb 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -182,7 +182,6 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, return -EINVAL; for (done = 0; done < nr_args; done++) { - struct io_rsrc_node *node; u64 tag = 0; if ((tags && copy_from_user(&tag, &tags[done], sizeof(tag))) || @@ -198,12 +197,9 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, continue; i = up->offset + done; - node = io_rsrc_node_lookup(&ctx->file_table.data, i); - if (node) { - io_put_rsrc_node(node); - ctx->file_table.data.nodes[i] = NULL; + if (io_reset_rsrc_node(&ctx->file_table.data, i)) io_file_bitmap_clear(&ctx->file_table, i); - } + if (fd != -1) { struct file *file = fget(fd); struct io_rsrc_node *node; @@ -281,9 +277,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, err = PTR_ERR(node); break; } - if (ctx->buf_table.nodes[i]) - io_put_rsrc_node(ctx->buf_table.nodes[i]); - + io_reset_rsrc_node(&ctx->buf_table, i); ctx->buf_table.nodes[i] = node; if (tag) node->tag = tag; diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 6952fb45f57a..abd214f303f5 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -85,6 +85,17 @@ static inline void io_put_rsrc_node(struct io_rsrc_node *node) io_free_rsrc_node(node); } +static inline bool io_reset_rsrc_node(struct io_rsrc_data *data, int index) +{ + struct io_rsrc_node *node = data->nodes[index]; + + if (!node) + return false; + io_put_rsrc_node(node); + data->nodes[index] = NULL; + return true; +} + static inline void io_req_put_rsrc_nodes(struct io_kiocb *req) { if (req->rsrc_nodes[IORING_RSRC_FILE] != rsrc_empty_node) {