From patchwork Sat Jan 12 21:30:10 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jens Axboe X-Patchwork-Id: 10761153 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 8C24D1580 for ; Sat, 12 Jan 2019 21:30:52 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 800F92902C for ; Sat, 12 Jan 2019 21:30:52 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 6D62429054; Sat, 12 Jan 2019 21:30:52 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.9 required=2.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,MAILING_LIST_MULTI,RCVD_IN_DNSWL_HI autolearn=unavailable version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id D288E29054 for ; Sat, 12 Jan 2019 21:30:51 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726708AbfALVat (ORCPT ); Sat, 12 Jan 2019 16:30:49 -0500 Received: from mail-pf1-f193.google.com ([209.85.210.193]:41216 "EHLO mail-pf1-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726696AbfALVas (ORCPT ); Sat, 12 Jan 2019 16:30:48 -0500 Received: by mail-pf1-f193.google.com with SMTP id b7so8560950pfi.8 for ; Sat, 12 Jan 2019 13:30:48 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20150623.gappssmtp.com; s=20150623; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=AW7jsIB6hNhqzBATRVyZlWxRkDXvAdFtbb95X+jyjmo=; b=B941y95GgMIADycRcE44Rk58D82fKFMpV+hUFgg3aRbhPofanzduRmenlpsRr9Kqhs xA+kFmktWCf+18x6/usAkBK0iAlu1/KaCN17i7pV5psxxDybo9XVfrEtiCcscUzBDZC6 qJi5cvePD3/1a44saLuy2tlqPbAHq1wjzZ9DhvA+RQmkbgcMqqovevXcpnoOGeXgUil2 boGyb4BJmv/8teAVGXtIWeWjKJUtyuYqMZY6cLe3Xlj0sgc4fsdabg5VlcETzFMIUHGO iz+lyBzQyLmev/YH+srcvfm/aIxeKnmEwMqEGyaYwV7t2cStbS5zHuJHJaOcI01jC+0f qE2w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=AW7jsIB6hNhqzBATRVyZlWxRkDXvAdFtbb95X+jyjmo=; b=iLuIjNbr3E6IQdk9FM+69NSNoDb5nyWBMNTmg4LH4B24iGxajdKfiCzktQK9Gu9Jsq A5bzTdeyzeADGmR2XTF+hJONnlp7fNPdvNPC1Z9FEbhCeEZWlWgrAJIVRHufY+bjkxhi 04fFQyOpFm9fDaxJNGwAoaOT5BR1/GmYZL60CeCID3Qa+IhdGjHcBGkMXj+lyBtdPqHH X5jU31ctYCL8XAmswjPQu/8bFlVUKBNQ0aFX32xrLgjy4zKSmMj1VUCmFVJRGlJHFF2l ViUrnCTi7UVMBxdAYpopdAOmu9RehwPtoRrO0vwyqjBB84+nZiqpZBY9CR7wRAe24ODx ZtIA== X-Gm-Message-State: AJcUukctULXhx7GvYdz6pcpNKbfH5eJ4xx/LXKWLE56zLBzPXuIT7NqX yqgryCRq1961Te+O3DXa9nL8fe7GuGbmPw== X-Google-Smtp-Source: ALg8bN7CJCZRLqA34VAoQHkLAyT9qeyJtUt5brK1P2LWiWnaAOgSU+j7wk+VcgfAAh3GHpX0yBSdmw== X-Received: by 2002:a63:1e17:: with SMTP id e23mr15596830pge.130.1547328647672; Sat, 12 Jan 2019 13:30:47 -0800 (PST) Received: from x1.localdomain (66.29.188.166.static.utbb.net. [66.29.188.166]) by smtp.gmail.com with ESMTPSA id y6sm151629818pfd.104.2019.01.12.13.30.45 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Sat, 12 Jan 2019 13:30:46 -0800 (PST) From: Jens Axboe To: linux-fsdevel@vger.kernel.org, linux-aio@kvack.org, linux-block@vger.kernel.org, linux-arch@vger.kernel.org Cc: hch@lst.de, jmoyer@redhat.com, avi@scylladb.com, Jens Axboe Subject: [PATCH 15/16] io_uring: add file registration Date: Sat, 12 Jan 2019 14:30:10 -0700 Message-Id: <20190112213011.1439-16-axboe@kernel.dk> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190112213011.1439-1-axboe@kernel.dk> References: <20190112213011.1439-1-axboe@kernel.dk> Sender: linux-fsdevel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP We normally have to fget/fput for each IO we do on a file. Even with the batching we do, this atomic inc/dec cost adds up. This adds IORING_REGISTER_FILES, and IORING_UNREGISTER_FILES opcodes for the io_uring_register(2) system call. Pass in an array of fds that are in use by the application, and we'll fget these for the duration of the io_uring context. When used, the application must set IOSQE_FIXED_FILE in the sqe->flags member. Then, instead of setting sqe->fd to the real fd, it sets sqe->fd to the index in the array passed in to IORING_REGISTER_FILES. Files are automatically unregistered when the io_uring context is torn down. An application need only unregister if it wishes to register a few set of fds. Signed-off-by: Jens Axboe --- fs/io_uring.c | 131 +++++++++++++++++++++++++++++----- include/uapi/linux/io_uring.h | 14 +++- 2 files changed, 127 insertions(+), 18 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 6f446d13b3d4..66a76f9fa7af 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -99,6 +99,10 @@ struct io_ring_ctx { struct io_mapped_ubuf *user_bufs; unsigned nr_user_bufs; + /* if used, fixed file set */ + struct file **user_files; + unsigned nr_user_files; + struct completion ctx_done; /* iopoll submission state */ @@ -137,6 +141,7 @@ struct io_kiocb { #define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */ #define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */ #define REQ_F_IOPOLL_EAGAIN 4 /* submission got EAGAIN */ +#define REQ_F_FIXED_FILE 8 /* ctx owns file */ u64 ki_user_data; }; @@ -355,15 +360,17 @@ static void io_iopoll_reap(struct io_ring_ctx *ctx, unsigned int *nr_events) * Batched puts of the same file, to avoid dirtying the * file usage count multiple times, if avoidable. */ - if (!file) { - file = req->rw.ki_filp; - file_count = 1; - } else if (file == req->rw.ki_filp) { - file_count++; - } else { - fput_many(file, file_count); - file = req->rw.ki_filp; - file_count = 1; + if (!(req->ki_flags & REQ_F_FIXED_FILE)) { + if (!file) { + file = req->rw.ki_filp; + file_count = 1; + } else if (file == req->rw.ki_filp) { + file_count++; + } else { + fput_many(file, file_count); + file = req->rw.ki_filp; + file_count = 1; + } } (*nr_events)++; @@ -557,13 +564,19 @@ static void io_fill_cq_error(struct io_ring_ctx *ctx, struct sqe_submit *s, wake_up(&ctx->wait); } +static void io_fput(struct io_kiocb *req) +{ + if (!(req->ki_flags & REQ_F_FIXED_FILE)) + fput(req->rw.ki_filp); +} + static void io_complete_scqring_rw(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); kiocb_end_write(kiocb); - fput(kiocb->ki_filp); + io_fput(req); io_cqring_fill_event(req->ki_ctx, req->ki_user_data, res, 0); io_free_req(req); } @@ -680,7 +693,17 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, struct kiocb *kiocb = &req->rw; int ret; - kiocb->ki_filp = io_file_get(state, sqe->fd); + if (unlikely(sqe->flags & ~IOSQE_FIXED_FILE)) + return -EINVAL; + + if (sqe->flags & IOSQE_FIXED_FILE) { + if (unlikely(!ctx->user_files || sqe->fd >= ctx->nr_user_files)) + return -EBADF; + kiocb->ki_filp = ctx->user_files[sqe->fd]; + req->ki_flags |= REQ_F_FIXED_FILE; + } else { + kiocb->ki_filp = io_file_get(state, sqe->fd); + } if (unlikely(!kiocb->ki_filp)) return -EBADF; kiocb->ki_pos = sqe->off; @@ -719,7 +742,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, } return 0; out_fput: - io_file_put(state, kiocb->ki_filp); + if (!(sqe->flags & IOSQE_FIXED_FILE)) + io_file_put(state, kiocb->ki_filp); return ret; } @@ -822,7 +846,7 @@ static ssize_t io_read(struct io_kiocb *req, const struct io_uring_sqe *sqe, kfree(iovec); out_fput: if (unlikely(ret)) - fput(file); + io_fput(req); return ret; } @@ -884,7 +908,7 @@ static ssize_t io_write(struct io_kiocb *req, const struct io_uring_sqe *sqe, } out_fput: if (unlikely(ret)) - fput(file); + io_fput(req); return ret; } @@ -902,19 +926,30 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (unlikely(req->ki_ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; + if (unlikely(sqe->flags & ~IOSQE_FIXED_FILE)) + return -EINVAL; if (unlikely(sqe->addr)) return -EINVAL; if (unlikely(sqe->fsync_flags & ~IORING_FSYNC_DATASYNC)) return -EINVAL; - file = fget(sqe->fd); + if (sqe->flags & IOSQE_FIXED_FILE) { + if (unlikely(!ctx->user_files || sqe->fd >= ctx->nr_user_files)) + return -EBADF; + file = ctx->user_files[sqe->fd]; + } else { + file = fget(sqe->fd); + } + if (unlikely(!file)) return -EBADF; ret = vfs_fsync_range(file, sqe->off, end > 0 ? end : LLONG_MAX, sqe->fsync_flags & IORING_FSYNC_DATASYNC); - fput(file); + if (!(sqe->flags & IOSQE_FIXED_FILE)) + fput(file); + io_cqring_fill_event(ctx, sqe->user_data, ret, 0); io_free_req(req); return 0; @@ -928,7 +963,7 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, ssize_t ret; /* enforce forwards compatibility on users */ - if (unlikely(sqe->flags || sqe->__pad2 || sqe->__pad3)) + if (unlikely(sqe->__pad2 || sqe->__pad3)) return -EINVAL; if (unlikely(s->index >= ctx->sq_entries)) @@ -1394,6 +1429,52 @@ static int __io_uring_enter(struct io_ring_ctx *ctx, unsigned to_submit, return ret; } +static int io_sqe_files_unregister(struct io_ring_ctx *ctx) +{ + int i; + + if (!ctx->user_files) + return -EINVAL; + + for (i = 0; i < ctx->nr_user_files; i++) + fput(ctx->user_files[i]); + + kfree(ctx->user_files); + ctx->user_files = NULL; + ctx->nr_user_files = 0; + return 0; +} + +static int io_sqe_files_register(struct io_ring_ctx *ctx, + struct io_uring_register_files *reg) +{ + int fd, i, ret = 0; + + ctx->user_files = kcalloc(reg->nr_fds, sizeof(struct file *), + GFP_KERNEL); + if (!ctx->user_files) + return -ENOMEM; + + for (i = 0; i < reg->nr_fds; i++) { + ret = -EFAULT; + if (copy_from_user(&fd, ®->fds[i], sizeof(fd))) + break; + + ctx->user_files[i] = fget(fd); + + ret = -EBADF; + if (!ctx->user_files[i]) + break; + ctx->nr_user_files++; + ret = 0; + } + + if (ret) + io_sqe_files_unregister(ctx); + + return ret; +} + static int io_sq_offload_start(struct io_ring_ctx *ctx, struct io_uring_params *p) { @@ -1615,6 +1696,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) io_sq_offload_stop(ctx); io_iopoll_reap_events(ctx); io_free_scq_urings(ctx); + io_sqe_files_unregister(ctx); io_sqe_buffer_unregister(ctx); percpu_ref_exit(&ctx->refs); kfree(ctx); @@ -1871,6 +1953,21 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_sqe_buffer_unregister(ctx); break; + case IORING_REGISTER_FILES: { + struct io_uring_register_files reg; + + ret = -EFAULT; + if (copy_from_user(®, arg, sizeof(reg))) + break; + ret = io_sqe_files_register(ctx, ®); + break; + } + case IORING_UNREGISTER_FILES: + ret = -EINVAL; + if (arg) + break; + ret = io_sqe_files_unregister(ctx); + break; default: ret = -EINVAL; break; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 7f9be0bd84ed..ffdaf46f19dd 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -16,7 +16,7 @@ */ struct io_uring_sqe { __u8 opcode; /* type of operation for this sqe */ - __u8 flags; /* as of now unused */ + __u8 flags; /* IOSQE_ flags */ __u16 ioprio; /* ioprio for the request */ __s32 fd; /* file descriptor to do IO on */ __u64 off; /* offset into file */ @@ -35,6 +35,11 @@ struct io_uring_sqe { __u64 user_data; /* data to be passed back at completion time */ }; +/* + * sqe->flags + */ +#define IOSQE_FIXED_FILE (1 << 0) /* use fixed fileset */ + /* * io_uring_setup() flags */ @@ -121,10 +126,17 @@ struct io_uring_params { */ #define IORING_REGISTER_BUFFERS 0 #define IORING_UNREGISTER_BUFFERS 1 +#define IORING_REGISTER_FILES 2 +#define IORING_UNREGISTER_FILES 3 struct io_uring_register_buffers { struct iovec *iovecs; __u32 nr_iovecs; }; +struct io_uring_register_files { + __s32 *fds; + __u32 nr_fds; +}; + #endif