From patchwork Wed Sep 13 15:27:37 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Breno Leitao X-Patchwork-Id: 13383310 X-Patchwork-Delegate: kuba@kernel.org Received: from lindbergh.monkeyblade.net (lindbergh.monkeyblade.net [23.128.96.19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id E2074A934; Wed, 13 Sep 2023 15:28:20 +0000 (UTC) Received: from mail-ej1-f47.google.com (mail-ej1-f47.google.com [209.85.218.47]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 38E47CCD; Wed, 13 Sep 2023 08:28:20 -0700 (PDT) Received: by mail-ej1-f47.google.com with SMTP id a640c23a62f3a-99c1d03e124so867744766b.2; Wed, 13 Sep 2023 08:28:20 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1694618898; x=1695223698; 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=T63D+iseOM6feL2ViRPYbx+xbxxkgrRy6waBaJFXQkc=; b=r0JDYjI2cbC89op4ypM56Lucvd/o0QrOrjFCoOnwuqf8paPw/YaaiOg8jA2FapF+if fj3In3b+UnWOv8v7TV+aBpzoTp1fJpqV2QHyzlNlG2WKF7aH1d6VSkWVmemIQ8DacD9m hTQu0q392R1rMW/9VdsjcHBz6sit7O3KiqZ/pnWWIbG8SNWB+lhKOjE67FXZlHaZhlQi 6YmM4ZJuz//WH3I5bi8TZU2BAnlfyZGOFSIYK8NlJUfVHnowMBoLUDXnJ1GfaoADrzzt lVsLLRM9NhAbvamcKoRlgwSUo3j5vo2yfwIP/JJ0nKYPC4gTfog/rzNls1AhhpNw6K43 JVQw== X-Gm-Message-State: AOJu0YyFS9csFcf4pGBzrEtRzuU6y2SXU5qlpsw5Wub/vn5ZXULjkwgG nzY0IURLNW4KzrtAhizhITGiTCHK0zM= X-Google-Smtp-Source: AGHT+IEMs9Boxfcw7qVlzVFEDeHVNXCAKXZD3Rz3ajV1O+cGsEythgRouzjpDE/rwGV0COfj4t+aeg== X-Received: by 2002:a17:906:18aa:b0:9a5:d83a:65be with SMTP id c10-20020a17090618aa00b009a5d83a65bemr2303502ejf.27.1694618898511; Wed, 13 Sep 2023 08:28:18 -0700 (PDT) Received: from localhost (fwdproxy-cln-005.fbsv.net. [2a03:2880:31ff:5::face:b00c]) by smtp.gmail.com with ESMTPSA id t14-20020a1709064f0e00b0099e05fb8f95sm8647352eju.137.2023.09.13.08.28.18 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Sep 2023 08:28:18 -0700 (PDT) From: Breno Leitao To: sdf@google.com, axboe@kernel.dk, asml.silence@gmail.com, willemdebruijn.kernel@gmail.com, kuba@kernel.org, pabeni@redhat.com, martin.lau@linux.dev, krisman@suse.de, "David S. Miller" , Eric Dumazet Cc: bpf@vger.kernel.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, io-uring@vger.kernel.org, Willem de Bruijn Subject: [PATCH v6 1/8] net/socket: Break down __sys_setsockopt Date: Wed, 13 Sep 2023 08:27:37 -0700 Message-Id: <20230913152744.2333228-2-leitao@debian.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230913152744.2333228-1-leitao@debian.org> References: <20230913152744.2333228-1-leitao@debian.org> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Patchwork-Delegate: kuba@kernel.org Split __sys_setsockopt() into two functions by removing the core logic into a sub-function (do_sock_setsockopt()). This will avoid code duplication when doing the same operation in other callers, for instance. do_sock_setsockopt() will be called by io_uring setsockopt() command operation in the following patch. Signed-off-by: Breno Leitao Reviewed-by: Willem de Bruijn --- include/net/sock.h | 2 ++ net/socket.c | 38 +++++++++++++++++++++++++------------- 2 files changed, 27 insertions(+), 13 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 11d503417591..aa8fb54ad0af 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1861,6 +1861,8 @@ int sk_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); +int do_sock_setsockopt(struct socket *sock, bool compat, int level, + int optname, char __user *user_optval, int optlen); int sk_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); diff --git a/net/socket.c b/net/socket.c index 77f28328e387..360332e098d4 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2261,31 +2261,22 @@ static bool sock_use_custom_sol_socket(const struct socket *sock) return test_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags); } -/* - * Set a socket option. Because we don't know the option lengths we have - * to pass the user mode parameter for the protocols to sort out. - */ -int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, - int optlen) +int do_sock_setsockopt(struct socket *sock, bool compat, int level, + int optname, char __user *user_optval, int optlen) { sockptr_t optval = USER_SOCKPTR(user_optval); const struct proto_ops *ops; char *kernel_optval = NULL; - int err, fput_needed; - struct socket *sock; + int err; if (optlen < 0) return -EINVAL; - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) - return err; - err = security_socket_setsockopt(sock, level, optname); if (err) goto out_put; - if (!in_compat_syscall()) + if (!compat) err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname, user_optval, &optlen, &kernel_optval); @@ -2308,6 +2299,27 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, optlen); kfree(kernel_optval); out_put: + return err; +} +EXPORT_SYMBOL(do_sock_setsockopt); + +/* Set a socket option. Because we don't know the option lengths we have + * to pass the user mode parameter for the protocols to sort out. + */ +int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, + int optlen) +{ + bool compat = in_compat_syscall(); + int err, fput_needed; + struct socket *sock; + + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if (!sock) + return err; + + err = do_sock_setsockopt(sock, compat, level, optname, user_optval, + optlen); + fput_light(sock->file, fput_needed); return err; } From patchwork Wed Sep 13 15:27:38 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Breno Leitao X-Patchwork-Id: 13383311 X-Patchwork-Delegate: kuba@kernel.org Received: from lindbergh.monkeyblade.net (lindbergh.monkeyblade.net [23.128.96.19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id EEFF61F937; Wed, 13 Sep 2023 15:28:22 +0000 (UTC) Received: from mail-lf1-f47.google.com (mail-lf1-f47.google.com [209.85.167.47]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 12B811BC3; Wed, 13 Sep 2023 08:28:22 -0700 (PDT) Received: by mail-lf1-f47.google.com with SMTP id 2adb3069b0e04-502e0b7875dso925656e87.0; Wed, 13 Sep 2023 08:28:21 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1694618900; x=1695223700; 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=HNDakB63GeZKBPdnx2EtHPN64oGZn+t0qvDI93lexvQ=; b=fvCHy6ZcoUIYrtFltO0XIziKj5/zzrXcoANIOXCNMIGvhE7dW4y/2RfYPpDblDZlIb hBTxL++nfoMUvP8wKbluFXmMSzDb+7+iZIEaKTrXbhlETCFMIQ7WwGRoB8YJtIq+PCq+ n+mP0F7cLlfiqwQ/xnMatPavlzjUiFZ0nF4nRwWDNt4ucOS6ukt/OEI/qTFlAocX0ZSP T65d74W3ZvXaf8sH8ngpAmWEoxiuXPPZ7Av5lLDVbNTxSfJ4D7lsWgr/QStFVlrJAZWh So65SFqEpkqeNTLn1wHgTv0T1mqSK8FVhe/+droqTT5lt2pcw67D+SMlHZSjZjGrB35G H5xw== X-Gm-Message-State: AOJu0YyD4hrFwSBwkpebL58O4cV7D9N1lzD9A5kbo4eVTnU+xLVf3CMi +T5eCPdAx5+vkGGBjwa5b0E= X-Google-Smtp-Source: AGHT+IHTNXupugjcqdM561DSjH0sQbE2ecX6oqqyTB94YrWwm5n/1rgUsWrwfNEHN7R4dgkuUMt4sg== X-Received: by 2002:ac2:53a9:0:b0:500:b64a:ad15 with SMTP id j9-20020ac253a9000000b00500b64aad15mr2104579lfh.52.1694618900057; Wed, 13 Sep 2023 08:28:20 -0700 (PDT) Received: from localhost (fwdproxy-cln-016.fbsv.net. [2a03:2880:31ff:10::face:b00c]) by smtp.gmail.com with ESMTPSA id n13-20020a170906b30d00b0099cc36c4681sm8596578ejz.157.2023.09.13.08.28.19 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Sep 2023 08:28:19 -0700 (PDT) From: Breno Leitao To: sdf@google.com, axboe@kernel.dk, asml.silence@gmail.com, willemdebruijn.kernel@gmail.com, kuba@kernel.org, pabeni@redhat.com, martin.lau@linux.dev, krisman@suse.de, "David S. Miller" , Eric Dumazet Cc: bpf@vger.kernel.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, io-uring@vger.kernel.org Subject: [PATCH v6 2/8] net/socket: Break down __sys_getsockopt Date: Wed, 13 Sep 2023 08:27:38 -0700 Message-Id: <20230913152744.2333228-3-leitao@debian.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230913152744.2333228-1-leitao@debian.org> References: <20230913152744.2333228-1-leitao@debian.org> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Patchwork-Delegate: kuba@kernel.org Split __sys_getsockopt() into two functions by removing the core logic into a sub-function (do_sock_getsockopt()). This will avoid code duplication when executing the same operation in other callers, for instance. do_sock_getsockopt() will be called by io_uring getsockopt() command operation in the following patch. Suggested-by: Martin KaFai Lau Signed-off-by: Breno Leitao --- include/net/sock.h | 3 +++ net/socket.c | 48 +++++++++++++++++++++++++++++----------------- 2 files changed, 33 insertions(+), 18 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index aa8fb54ad0af..fbd568a43d28 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1863,6 +1863,9 @@ int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); int do_sock_setsockopt(struct socket *sock, bool compat, int level, int optname, char __user *user_optval, int optlen); +int do_sock_getsockopt(struct socket *sock, bool compat, int level, + int optname, char __user *user_optval, + int __user *user_optlen); int sk_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); diff --git a/net/socket.c b/net/socket.c index 360332e098d4..fb943602186e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2333,28 +2333,17 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, int optname)); -/* - * Get a socket option. Because we don't know the option lengths we have - * to pass a user mode parameter for the protocols to sort out. - */ -int __sys_getsockopt(int fd, int level, int optname, char __user *optval, - int __user *optlen) +int do_sock_getsockopt(struct socket *sock, bool compat, int level, + int optname, char __user *optval, + int __user *optlen) { int max_optlen __maybe_unused; const struct proto_ops *ops; - int err, fput_needed; - struct socket *sock; - - sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) - return err; + int err; err = security_socket_getsockopt(sock, level, optname); if (err) - goto out_put; - - if (!in_compat_syscall()) - max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); + return err; ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET) @@ -2365,11 +2354,34 @@ int __sys_getsockopt(int fd, int level, int optname, char __user *optval, err = ops->getsockopt(sock, level, optname, optval, optlen); - if (!in_compat_syscall()) + if (!compat) { + max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, optval, optlen, max_optlen, err); -out_put: + } + + return err; +} +EXPORT_SYMBOL(do_sock_getsockopt); + +/* Get a socket option. Because we don't know the option lengths we have + * to pass a user mode parameter for the protocols to sort out. + */ +int __sys_getsockopt(int fd, int level, int optname, char __user *optval, + int __user *optlen) +{ + bool compat = in_compat_syscall(); + int err, fput_needed; + struct socket *sock; + + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if (!sock) + return err; + + err = do_sock_getsockopt(sock, compat, level, optname, optval, + optlen); + fput_light(sock->file, fput_needed); return err; } From patchwork Wed Sep 13 15:27:39 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Breno Leitao X-Patchwork-Id: 13383312 Received: from lindbergh.monkeyblade.net (lindbergh.monkeyblade.net [23.128.96.19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 4182A1EA8F; Wed, 13 Sep 2023 15:28:24 +0000 (UTC) Received: from mail-lf1-f49.google.com (mail-lf1-f49.google.com [209.85.167.49]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 794111BC9; Wed, 13 Sep 2023 08:28:23 -0700 (PDT) Received: by mail-lf1-f49.google.com with SMTP id 2adb3069b0e04-50098cc8967so11230224e87.1; Wed, 13 Sep 2023 08:28:23 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1694618902; x=1695223702; 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=+vvxyHXTfiSW+8d09yTsLSiY7Ry74wlSEWGj/O1wQD8=; b=ID3aFaZrNBfatNHIcF2NhNrJIe4CRwfzK1LnEMS+UWByX5zZqaEFxRRYdSFrRwDwy+ aNW7Q1nsuGzP7dJtrYxscAaRZWHnl1APV8enrlZ+27UWhn9kJhcLGQkqe04OwN82OsFz Q/WgW9/28cKN3p5bpukpjCH3hrf9QDummyU6I6WZZuytCK5C/eWiN0XoiXTVv3tWrpSm niVoPVTPrrJY6a3lQEX6hzkiOK5QXk2on4NbZBT2rsO4aFolozc1+hDbzETk9a2QSClI 3y444Zr3BkgudiyHzsJnaBRZ6l4HZzPGzA27v1Kh1d/IZCEIfrv8AkuY/4hbEwV6RGSv 7CHA== X-Gm-Message-State: AOJu0YzIBropAgKvxi40wTJe7b3a4PHGDvxeLssJqbqSrvVWIghiazHG LmnAxa5125iMx11ingdvHho= X-Google-Smtp-Source: AGHT+IFkDHP8efksOvVhO+b094unbQdjltuvg/Q7103ZxOgGHV9iGnK7Ay3GrpY/UFr/gRMRmdwR2w== X-Received: by 2002:a05:6512:3e17:b0:4fe:676:8c0b with SMTP id i23-20020a0565123e1700b004fe06768c0bmr3139980lfv.11.1694618901572; Wed, 13 Sep 2023 08:28:21 -0700 (PDT) Received: from localhost (fwdproxy-cln-017.fbsv.net. [2a03:2880:31ff:11::face:b00c]) by smtp.gmail.com with ESMTPSA id oz13-20020a170906cd0d00b0098951bb4dc3sm8608469ejb.184.2023.09.13.08.28.21 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Sep 2023 08:28:21 -0700 (PDT) From: Breno Leitao To: sdf@google.com, axboe@kernel.dk, asml.silence@gmail.com, willemdebruijn.kernel@gmail.com, kuba@kernel.org, pabeni@redhat.com, martin.lau@linux.dev, krisman@suse.de Cc: bpf@vger.kernel.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, io-uring@vger.kernel.org Subject: [PATCH v6 3/8] io_uring/cmd: Pass compat mode in issue_flags Date: Wed, 13 Sep 2023 08:27:39 -0700 Message-Id: <20230913152744.2333228-4-leitao@debian.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230913152744.2333228-1-leitao@debian.org> References: <20230913152744.2333228-1-leitao@debian.org> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Create a new flag to track if the operation is running compat mode. This basically check the context->compat and pass it to the issue_flags, so, it could be queried later in the callbacks. Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Breno Leitao --- include/linux/io_uring.h | 1 + io_uring/uring_cmd.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 106cdc55ff3b..bc53b35966ed 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -20,6 +20,7 @@ enum io_uring_cmd_flags { IO_URING_F_SQE128 = (1 << 8), IO_URING_F_CQE32 = (1 << 9), IO_URING_F_IOPOLL = (1 << 10), + IO_URING_F_COMPAT = (1 << 11), }; struct io_uring_cmd { diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 537795fddc87..60f843a357e0 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -128,6 +128,8 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) issue_flags |= IO_URING_F_SQE128; if (ctx->flags & IORING_SETUP_CQE32) issue_flags |= IO_URING_F_CQE32; + if (ctx->compat) + issue_flags |= IO_URING_F_COMPAT; if (ctx->flags & IORING_SETUP_IOPOLL) { if (!file->f_op->uring_cmd_iopoll) return -EOPNOTSUPP; From patchwork Wed Sep 13 15:27:40 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Breno Leitao X-Patchwork-Id: 13383313 X-Patchwork-Delegate: kuba@kernel.org Received: from lindbergh.monkeyblade.net (lindbergh.monkeyblade.net [23.128.96.19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 681721A736; Wed, 13 Sep 2023 15:28:33 +0000 (UTC) Received: from mail-ed1-f45.google.com (mail-ed1-f45.google.com [209.85.208.45]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 5F50F1BDC; Wed, 13 Sep 2023 08:28:32 -0700 (PDT) Received: by mail-ed1-f45.google.com with SMTP id 4fb4d7f45d1cf-52a250aa012so8971770a12.3; Wed, 13 Sep 2023 08:28:32 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1694618911; x=1695223711; 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=HzQ2L3VA3K1qXdfZEOlnENEcthLwu4DsWTTSpmxxUbA=; b=VrCxKy3gVQL3CNibU6StX8GECh4MpChUUWRlG7FbItfiO5ucoIMz1tDSXpStYIBaNE 4YOSqUumfZqMTLPcvJV7KpL73ZqqLejOoEofafQh7X+oOpTbZ/P430hdiBzz4gg1RTR+ iaatU66j7wArEbc3GKmGLdINNEqOTmjcTn1oXco57WInC7eNMOlXGPxxjckV43hTJ6Op glK2vWeOj2c/S1ZZ9Yuj/IXusRhCmqF1Su/qW3JJBILw8xMLfhLvOCQlsHSbfHtigG+k I1BrGeBANRdprjVL7X8Mt5aU3flMBlwP2v7CMWgeJayEMlekt/kSqks9BBQWHyymgGYH nfYQ== X-Gm-Message-State: AOJu0YxgcedgtQppuc7IPxSDgSOdHpzGBtCrSkSL9X+QrbuQmCmPGB+H pN+bm8uRmhO7OWGhEowTAMU= X-Google-Smtp-Source: AGHT+IHk/d9u4T5S/Eh02VQs1hlR8l1ehgTasQFiY5U6ClaM5boWnPrrORT6E8+2hOSYddN8Yk0vUQ== X-Received: by 2002:a17:906:3091:b0:9a5:c944:8e71 with SMTP id 17-20020a170906309100b009a5c9448e71mr2187858ejv.60.1694618910695; Wed, 13 Sep 2023 08:28:30 -0700 (PDT) Received: from localhost (fwdproxy-cln-000.fbsv.net. [2a03:2880:31ff::face:b00c]) by smtp.gmail.com with ESMTPSA id t1-20020a170906268100b0099cce6f7d50sm8586983ejc.64.2023.09.13.08.28.30 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Sep 2023 08:28:30 -0700 (PDT) From: Breno Leitao To: sdf@google.com, axboe@kernel.dk, asml.silence@gmail.com, willemdebruijn.kernel@gmail.com, kuba@kernel.org, pabeni@redhat.com, martin.lau@linux.dev, krisman@suse.de, "David S. Miller" , Eric Dumazet , Shuah Khan Cc: bpf@vger.kernel.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, io-uring@vger.kernel.org, linux-kselftest@vger.kernel.org (open list:KERNEL SELFTEST FRAMEWORK) Subject: [PATCH v6 4/8] selftests/net: Extract uring helpers to be reusable Date: Wed, 13 Sep 2023 08:27:40 -0700 Message-Id: <20230913152744.2333228-5-leitao@debian.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230913152744.2333228-1-leitao@debian.org> References: <20230913152744.2333228-1-leitao@debian.org> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Patchwork-Delegate: kuba@kernel.org Instead of defining basic io_uring functions in the test case, move them to a common directory, so, other tests can use them. This simplify the test code and reuse the common liburing infrastructure. This is basically a copy of what we have in io_uring_zerocopy_tx with some minor improvements to make checkpatch happy. A follow-up test will use the same helpers in a BPF sockopt test. Signed-off-by: Breno Leitao --- tools/include/io_uring/mini_liburing.h | 292 ++++++++++++++++++ tools/testing/selftests/net/Makefile | 1 + .../selftests/net/io_uring_zerocopy_tx.c | 268 +--------------- 3 files changed, 295 insertions(+), 266 deletions(-) create mode 100644 tools/include/io_uring/mini_liburing.h diff --git a/tools/include/io_uring/mini_liburing.h b/tools/include/io_uring/mini_liburing.h new file mode 100644 index 000000000000..e0e1e76def25 --- /dev/null +++ b/tools/include/io_uring/mini_liburing.h @@ -0,0 +1,292 @@ +/* SPDX-License-Identifier: MIT */ + +#include +#include +#include +#include +#include +#include + +struct io_sq_ring { + unsigned int *head; + unsigned int *tail; + unsigned int *ring_mask; + unsigned int *ring_entries; + unsigned int *flags; + unsigned int *array; +}; + +struct io_cq_ring { + unsigned int *head; + unsigned int *tail; + unsigned int *ring_mask; + unsigned int *ring_entries; + struct io_uring_cqe *cqes; +}; + +struct io_uring_sq { + unsigned int *khead; + unsigned int *ktail; + unsigned int *kring_mask; + unsigned int *kring_entries; + unsigned int *kflags; + unsigned int *kdropped; + unsigned int *array; + struct io_uring_sqe *sqes; + + unsigned int sqe_head; + unsigned int sqe_tail; + + size_t ring_sz; +}; + +struct io_uring_cq { + unsigned int *khead; + unsigned int *ktail; + unsigned int *kring_mask; + unsigned int *kring_entries; + unsigned int *koverflow; + struct io_uring_cqe *cqes; + + size_t ring_sz; +}; + +struct io_uring { + struct io_uring_sq sq; + struct io_uring_cq cq; + int ring_fd; +}; + +#if defined(__x86_64) || defined(__i386__) +#define read_barrier() __asm__ __volatile__("":::"memory") +#define write_barrier() __asm__ __volatile__("":::"memory") +#else +#define read_barrier() __sync_synchronize() +#define write_barrier() __sync_synchronize() +#endif + +static inline int io_uring_mmap(int fd, struct io_uring_params *p, + struct io_uring_sq *sq, struct io_uring_cq *cq) +{ + size_t size; + void *ptr; + int ret; + + sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned int); + ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING); + if (ptr == MAP_FAILED) + return -errno; + sq->khead = ptr + p->sq_off.head; + sq->ktail = ptr + p->sq_off.tail; + sq->kring_mask = ptr + p->sq_off.ring_mask; + sq->kring_entries = ptr + p->sq_off.ring_entries; + sq->kflags = ptr + p->sq_off.flags; + sq->kdropped = ptr + p->sq_off.dropped; + sq->array = ptr + p->sq_off.array; + + size = p->sq_entries * sizeof(struct io_uring_sqe); + sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQES); + if (sq->sqes == MAP_FAILED) { + ret = -errno; +err: + munmap(sq->khead, sq->ring_sz); + return ret; + } + + cq->ring_sz = p->cq_off.cqes + p->cq_entries * sizeof(struct io_uring_cqe); + ptr = mmap(0, cq->ring_sz, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_CQ_RING); + if (ptr == MAP_FAILED) { + ret = -errno; + munmap(sq->sqes, p->sq_entries * sizeof(struct io_uring_sqe)); + goto err; + } + cq->khead = ptr + p->cq_off.head; + cq->ktail = ptr + p->cq_off.tail; + cq->kring_mask = ptr + p->cq_off.ring_mask; + cq->kring_entries = ptr + p->cq_off.ring_entries; + cq->koverflow = ptr + p->cq_off.overflow; + cq->cqes = ptr + p->cq_off.cqes; + return 0; +} + +static inline int io_uring_setup(unsigned int entries, + struct io_uring_params *p) +{ + return syscall(__NR_io_uring_setup, entries, p); +} + +static inline int io_uring_enter(int fd, unsigned int to_submit, + unsigned int min_complete, + unsigned int flags, sigset_t *sig) +{ + return syscall(__NR_io_uring_enter, fd, to_submit, min_complete, + flags, sig, _NSIG / 8); +} + +static inline int io_uring_queue_init(unsigned int entries, + struct io_uring *ring, + unsigned int flags) +{ + struct io_uring_params p; + int fd, ret; + + memset(ring, 0, sizeof(*ring)); + memset(&p, 0, sizeof(p)); + p.flags = flags; + + fd = io_uring_setup(entries, &p); + if (fd < 0) + return fd; + ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq); + if (!ret) + ring->ring_fd = fd; + else + close(fd); + return ret; +} + +/* Get a sqe */ +static inline struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring) +{ + struct io_uring_sq *sq = &ring->sq; + + if (sq->sqe_tail + 1 - sq->sqe_head > *sq->kring_entries) + return NULL; + return &sq->sqes[sq->sqe_tail++ & *sq->kring_mask]; +} + +static inline int io_uring_wait_cqe(struct io_uring *ring, + struct io_uring_cqe **cqe_ptr) +{ + struct io_uring_cq *cq = &ring->cq; + const unsigned int mask = *cq->kring_mask; + unsigned int head = *cq->khead; + int ret; + + *cqe_ptr = NULL; + do { + read_barrier(); + if (head != *cq->ktail) { + *cqe_ptr = &cq->cqes[head & mask]; + break; + } + ret = io_uring_enter(ring->ring_fd, 0, 1, + IORING_ENTER_GETEVENTS, NULL); + if (ret < 0) + return -errno; + } while (1); + + return 0; +} + +static inline int io_uring_submit(struct io_uring *ring) +{ + struct io_uring_sq *sq = &ring->sq; + const unsigned int mask = *sq->kring_mask; + unsigned int ktail, submitted, to_submit; + int ret; + + read_barrier(); + if (*sq->khead != *sq->ktail) { + submitted = *sq->kring_entries; + goto submit; + } + if (sq->sqe_head == sq->sqe_tail) + return 0; + + ktail = *sq->ktail; + to_submit = sq->sqe_tail - sq->sqe_head; + for (submitted = 0; submitted < to_submit; submitted++) { + read_barrier(); + sq->array[ktail++ & mask] = sq->sqe_head++ & mask; + } + if (!submitted) + return 0; + + if (*sq->ktail != ktail) { + write_barrier(); + *sq->ktail = ktail; + write_barrier(); + } +submit: + ret = io_uring_enter(ring->ring_fd, submitted, 0, + IORING_ENTER_GETEVENTS, NULL); + return ret < 0 ? -errno : ret; +} + +static inline void io_uring_queue_exit(struct io_uring *ring) +{ + struct io_uring_sq *sq = &ring->sq; + + munmap(sq->sqes, *sq->kring_entries * sizeof(struct io_uring_sqe)); + munmap(sq->khead, sq->ring_sz); + close(ring->ring_fd); +} + +/* Prepare and send the SQE */ +static inline void io_uring_prep_cmd(struct io_uring_sqe *sqe, int op, + int sockfd, + int level, int optname, + const void *optval, + const socklen_t optlen) +{ + memset(sqe, 0, sizeof(*sqe)); + sqe->opcode = (__u8)IORING_OP_URING_CMD; + sqe->fd = sockfd; + sqe->cmd_op = op; + + sqe->level = level; + sqe->optname = optname; + sqe->optval = (unsigned long long)optval; + sqe->optlen = (unsigned long long)optlen; +} + +static inline void io_uring_prep_cmd_get(struct io_uring_sqe *sqe, int op, + int sockfd, + int level, int optname, + const void *optval, + const socklen_t *optlen) +{ + io_uring_prep_cmd(sqe, op, sockfd, level, optname, optval, 0); + sqe->optlen = (unsigned long long)optlen; +} + +static inline int io_uring_register_buffers(struct io_uring *ring, + const struct iovec *iovecs, + unsigned int nr_iovecs) +{ + int ret; + + ret = syscall(__NR_io_uring_register, ring->ring_fd, + IORING_REGISTER_BUFFERS, iovecs, nr_iovecs); + return (ret < 0) ? -errno : ret; +} + +static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd, + const void *buf, size_t len, int flags) +{ + memset(sqe, 0, sizeof(*sqe)); + sqe->opcode = (__u8)IORING_OP_SEND; + sqe->fd = sockfd; + sqe->addr = (unsigned long)buf; + sqe->len = len; + sqe->msg_flags = (__u32)flags; +} + +static inline void io_uring_prep_sendzc(struct io_uring_sqe *sqe, int sockfd, + const void *buf, size_t len, int flags, + unsigned int zc_flags) +{ + io_uring_prep_send(sqe, sockfd, buf, len, flags); + sqe->opcode = (__u8)IORING_OP_SEND_ZC; + sqe->ioprio = zc_flags; +} + +static inline void io_uring_cqe_seen(struct io_uring *ring) +{ + *(&ring->cq)->khead += 1; + write_barrier(); +} diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 8b017070960d..f8d99837b9dc 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -98,6 +98,7 @@ $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread -lcrypto $(OUTPUT)/tcp_inq: LDLIBS += -lpthread $(OUTPUT)/bind_bhash: LDLIBS += -lpthread +$(OUTPUT)/io_uring_zerocopy_tx: CFLAGS += -I../../../include/ # Rules to generate bpf obj nat6to4.o CLANG ?= clang diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.c b/tools/testing/selftests/net/io_uring_zerocopy_tx.c index 154287740172..76e604e4810e 100644 --- a/tools/testing/selftests/net/io_uring_zerocopy_tx.c +++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.c @@ -36,6 +36,8 @@ #include #include +#include + #define NOTIF_TAG 0xfffffffULL #define NONZC_TAG 0 #define ZC_TAG 1 @@ -60,272 +62,6 @@ static struct sockaddr_storage cfg_dst_addr; static char payload[IP_MAXPACKET] __attribute__((aligned(4096))); -struct io_sq_ring { - unsigned *head; - unsigned *tail; - unsigned *ring_mask; - unsigned *ring_entries; - unsigned *flags; - unsigned *array; -}; - -struct io_cq_ring { - unsigned *head; - unsigned *tail; - unsigned *ring_mask; - unsigned *ring_entries; - struct io_uring_cqe *cqes; -}; - -struct io_uring_sq { - unsigned *khead; - unsigned *ktail; - unsigned *kring_mask; - unsigned *kring_entries; - unsigned *kflags; - unsigned *kdropped; - unsigned *array; - struct io_uring_sqe *sqes; - - unsigned sqe_head; - unsigned sqe_tail; - - size_t ring_sz; -}; - -struct io_uring_cq { - unsigned *khead; - unsigned *ktail; - unsigned *kring_mask; - unsigned *kring_entries; - unsigned *koverflow; - struct io_uring_cqe *cqes; - - size_t ring_sz; -}; - -struct io_uring { - struct io_uring_sq sq; - struct io_uring_cq cq; - int ring_fd; -}; - -#ifdef __alpha__ -# ifndef __NR_io_uring_setup -# define __NR_io_uring_setup 535 -# endif -# ifndef __NR_io_uring_enter -# define __NR_io_uring_enter 536 -# endif -# ifndef __NR_io_uring_register -# define __NR_io_uring_register 537 -# endif -#else /* !__alpha__ */ -# ifndef __NR_io_uring_setup -# define __NR_io_uring_setup 425 -# endif -# ifndef __NR_io_uring_enter -# define __NR_io_uring_enter 426 -# endif -# ifndef __NR_io_uring_register -# define __NR_io_uring_register 427 -# endif -#endif - -#if defined(__x86_64) || defined(__i386__) -#define read_barrier() __asm__ __volatile__("":::"memory") -#define write_barrier() __asm__ __volatile__("":::"memory") -#else - -#define read_barrier() __sync_synchronize() -#define write_barrier() __sync_synchronize() -#endif - -static int io_uring_setup(unsigned int entries, struct io_uring_params *p) -{ - return syscall(__NR_io_uring_setup, entries, p); -} - -static int io_uring_enter(int fd, unsigned int to_submit, - unsigned int min_complete, - unsigned int flags, sigset_t *sig) -{ - return syscall(__NR_io_uring_enter, fd, to_submit, min_complete, - flags, sig, _NSIG / 8); -} - -static int io_uring_register_buffers(struct io_uring *ring, - const struct iovec *iovecs, - unsigned nr_iovecs) -{ - int ret; - - ret = syscall(__NR_io_uring_register, ring->ring_fd, - IORING_REGISTER_BUFFERS, iovecs, nr_iovecs); - return (ret < 0) ? -errno : ret; -} - -static int io_uring_mmap(int fd, struct io_uring_params *p, - struct io_uring_sq *sq, struct io_uring_cq *cq) -{ - size_t size; - void *ptr; - int ret; - - sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned); - ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING); - if (ptr == MAP_FAILED) - return -errno; - sq->khead = ptr + p->sq_off.head; - sq->ktail = ptr + p->sq_off.tail; - sq->kring_mask = ptr + p->sq_off.ring_mask; - sq->kring_entries = ptr + p->sq_off.ring_entries; - sq->kflags = ptr + p->sq_off.flags; - sq->kdropped = ptr + p->sq_off.dropped; - sq->array = ptr + p->sq_off.array; - - size = p->sq_entries * sizeof(struct io_uring_sqe); - sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQES); - if (sq->sqes == MAP_FAILED) { - ret = -errno; -err: - munmap(sq->khead, sq->ring_sz); - return ret; - } - - cq->ring_sz = p->cq_off.cqes + p->cq_entries * sizeof(struct io_uring_cqe); - ptr = mmap(0, cq->ring_sz, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_CQ_RING); - if (ptr == MAP_FAILED) { - ret = -errno; - munmap(sq->sqes, p->sq_entries * sizeof(struct io_uring_sqe)); - goto err; - } - cq->khead = ptr + p->cq_off.head; - cq->ktail = ptr + p->cq_off.tail; - cq->kring_mask = ptr + p->cq_off.ring_mask; - cq->kring_entries = ptr + p->cq_off.ring_entries; - cq->koverflow = ptr + p->cq_off.overflow; - cq->cqes = ptr + p->cq_off.cqes; - return 0; -} - -static int io_uring_queue_init(unsigned entries, struct io_uring *ring, - unsigned flags) -{ - struct io_uring_params p; - int fd, ret; - - memset(ring, 0, sizeof(*ring)); - memset(&p, 0, sizeof(p)); - p.flags = flags; - - fd = io_uring_setup(entries, &p); - if (fd < 0) - return fd; - ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq); - if (!ret) - ring->ring_fd = fd; - else - close(fd); - return ret; -} - -static int io_uring_submit(struct io_uring *ring) -{ - struct io_uring_sq *sq = &ring->sq; - const unsigned mask = *sq->kring_mask; - unsigned ktail, submitted, to_submit; - int ret; - - read_barrier(); - if (*sq->khead != *sq->ktail) { - submitted = *sq->kring_entries; - goto submit; - } - if (sq->sqe_head == sq->sqe_tail) - return 0; - - ktail = *sq->ktail; - to_submit = sq->sqe_tail - sq->sqe_head; - for (submitted = 0; submitted < to_submit; submitted++) { - read_barrier(); - sq->array[ktail++ & mask] = sq->sqe_head++ & mask; - } - if (!submitted) - return 0; - - if (*sq->ktail != ktail) { - write_barrier(); - *sq->ktail = ktail; - write_barrier(); - } -submit: - ret = io_uring_enter(ring->ring_fd, submitted, 0, - IORING_ENTER_GETEVENTS, NULL); - return ret < 0 ? -errno : ret; -} - -static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd, - const void *buf, size_t len, int flags) -{ - memset(sqe, 0, sizeof(*sqe)); - sqe->opcode = (__u8) IORING_OP_SEND; - sqe->fd = sockfd; - sqe->addr = (unsigned long) buf; - sqe->len = len; - sqe->msg_flags = (__u32) flags; -} - -static inline void io_uring_prep_sendzc(struct io_uring_sqe *sqe, int sockfd, - const void *buf, size_t len, int flags, - unsigned zc_flags) -{ - io_uring_prep_send(sqe, sockfd, buf, len, flags); - sqe->opcode = (__u8) IORING_OP_SEND_ZC; - sqe->ioprio = zc_flags; -} - -static struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring) -{ - struct io_uring_sq *sq = &ring->sq; - - if (sq->sqe_tail + 1 - sq->sqe_head > *sq->kring_entries) - return NULL; - return &sq->sqes[sq->sqe_tail++ & *sq->kring_mask]; -} - -static int io_uring_wait_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr) -{ - struct io_uring_cq *cq = &ring->cq; - const unsigned mask = *cq->kring_mask; - unsigned head = *cq->khead; - int ret; - - *cqe_ptr = NULL; - do { - read_barrier(); - if (head != *cq->ktail) { - *cqe_ptr = &cq->cqes[head & mask]; - break; - } - ret = io_uring_enter(ring->ring_fd, 0, 1, - IORING_ENTER_GETEVENTS, NULL); - if (ret < 0) - return -errno; - } while (1); - - return 0; -} - -static inline void io_uring_cqe_seen(struct io_uring *ring) -{ - *(&ring->cq)->khead += 1; - write_barrier(); -} - static unsigned long gettimeofday_ms(void) { struct timeval tv; From patchwork Wed Sep 13 15:27:41 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Breno Leitao X-Patchwork-Id: 13383314 Received: from lindbergh.monkeyblade.net (lindbergh.monkeyblade.net [23.128.96.19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id DA6BD1A736; Wed, 13 Sep 2023 15:28:34 +0000 (UTC) Received: from mail-lf1-f49.google.com (mail-lf1-f49.google.com [209.85.167.49]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id DD7BC1BE9; Wed, 13 Sep 2023 08:28:33 -0700 (PDT) Received: by mail-lf1-f49.google.com with SMTP id 2adb3069b0e04-502b0d23f28so6812681e87.2; Wed, 13 Sep 2023 08:28:33 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1694618912; x=1695223712; 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=rF5iM8ZkJqphGmjRFU1s0SbK7ImZ/Xg4gUBQOimY8QI=; b=i6HhVNKpabsOIC2vJKOGy/osVxXwPvIZ/0kg4nRvpeW7rlqSCb1WtpJvR0lMM09S17 J8HcNioLp2n4DbmP/s0PE+Cx37xLFQnqsGTt1q5oV+0tjQhOUnO2s2g4YpDqr0hcZpVV +wmiSyFHqRk7c/FXKqZ9/7odXustALINmGb73P30w0ZsdZwdZClnRaeqlh045jqSqYNJ P3h8eSIEfmfPOedoXjUZ6fCEau/tQETJjAY2+BgBFCdjibIpPxcTmXIEwWLLfxh9NUfo myMzxPlTF/YHEq1UnJuzKhkuwVGZf/dBtk85RChMXTsJOEiWtS+Lrh8mEBGe+f+W2ELg JcXA== X-Gm-Message-State: AOJu0Yy1OmCJGvkJJiddeQWIz0PrJy5qLdOPyI3QzvaFOlcNkez8eFY5 rEWUHMNu7+aLuEEsWmHwWXQ= X-Google-Smtp-Source: AGHT+IFeaXyIkMgF9AuqjzrWL2PW3mVfMdv3z6auaM6K/CEvS2+FXH/TE2OedM1zhhL7jlvLu+syIA== X-Received: by 2002:a19:2d08:0:b0:4fe:1681:9378 with SMTP id k8-20020a192d08000000b004fe16819378mr2448500lfj.66.1694618912053; Wed, 13 Sep 2023 08:28:32 -0700 (PDT) Received: from localhost (fwdproxy-cln-001.fbsv.net. [2a03:2880:31ff:1::face:b00c]) by smtp.gmail.com with ESMTPSA id kj27-20020a170907765b00b0099b5a71b0bfsm8705015ejc.94.2023.09.13.08.28.31 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Sep 2023 08:28:31 -0700 (PDT) From: Breno Leitao To: sdf@google.com, axboe@kernel.dk, asml.silence@gmail.com, willemdebruijn.kernel@gmail.com, kuba@kernel.org, pabeni@redhat.com, martin.lau@linux.dev, krisman@suse.de Cc: bpf@vger.kernel.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, io-uring@vger.kernel.org Subject: [PATCH v6 5/8] io_uring/cmd: return -EOPNOTSUPP if net is disabled Date: Wed, 13 Sep 2023 08:27:41 -0700 Message-Id: <20230913152744.2333228-6-leitao@debian.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230913152744.2333228-1-leitao@debian.org> References: <20230913152744.2333228-1-leitao@debian.org> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Protect io_uring_cmd_sock() to be called if CONFIG_NET is not set. If network is not enabled, but io_uring is, then we want to return -EOPNOTSUPP for any possible socket operation. This is helpful because io_uring_cmd_sock() can now call functions that only exits if CONFIG_NET is enabled without having #ifdef CONFIG_NET inside the function itself. Signed-off-by: Breno Leitao --- io_uring/uring_cmd.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 60f843a357e0..5753c3611b74 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -167,6 +167,7 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, } EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed); +#if defined(CONFIG_NET) int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) { struct socket *sock = cmd->file->private_data; @@ -193,3 +194,4 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) } } EXPORT_SYMBOL_GPL(io_uring_cmd_sock); +#endif From patchwork Wed Sep 13 15:27:42 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Breno Leitao X-Patchwork-Id: 13383315 Received: from lindbergh.monkeyblade.net (lindbergh.monkeyblade.net [23.128.96.19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 0A64C200BA; Wed, 13 Sep 2023 15:28:36 +0000 (UTC) Received: from mail-ed1-f48.google.com (mail-ed1-f48.google.com [209.85.208.48]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 15F4B1BF2; Wed, 13 Sep 2023 08:28:35 -0700 (PDT) Received: by mail-ed1-f48.google.com with SMTP id 4fb4d7f45d1cf-52f31fb26e2so5405107a12.3; Wed, 13 Sep 2023 08:28:34 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1694618913; x=1695223713; 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=lDiXjrFRlF6VHQWvFjoZXtrdxjTNkGukVcEtNKPtPXI=; b=Sh3e4sFKi8aoMbuK3oScZ0WdKdjGR+lB9KaHR3tb17jej2kpnaMCNIJ2kbztNYGqzw fI2JXxV6k/Bs77yN1D/jXD/r3cpbjsejG3cpe3vhINoxUFqUYK/WI31nhXWn7/xt1FCw m3y1pV21Z8bpzrhvKlmAHX8vmyn7ZCeDS8nz9jCyKh+us2EA3l4HAlHvLVt1xFap/0qI NKn6BzGLsk2I3UJEc+zi0mfZOlLi9HevJM7gy4NCsVy2Gh3RlHHVUhzwgmg/Y0bhB6Er LM7E4uJXqlUQxF0moNLFd6j6doNMnTD/pTc1ONYrT/+uHU/ToFTYFGrOdUs6GsZu8XMC vj+w== X-Gm-Message-State: AOJu0YxwbNAaFJmFJg7CzTwHYmNG6JZw8ZXQQ9TiEx4YgRtoTiGYu31Z 7cBXC43QgGipnPvDM2YWQEk= X-Google-Smtp-Source: AGHT+IFJQ2QuwiDxVrXozbquE3kCcqCx0DzLR5CvSuQnKYXRWIr8XPDK0iLZz5VQw3qTo/IS6L25YQ== X-Received: by 2002:a05:6402:1b04:b0:523:d1e0:7079 with SMTP id by4-20020a0564021b0400b00523d1e07079mr2423946edb.21.1694618913506; Wed, 13 Sep 2023 08:28:33 -0700 (PDT) Received: from localhost (fwdproxy-cln-009.fbsv.net. [2a03:2880:31ff:9::face:b00c]) by smtp.gmail.com with ESMTPSA id c2-20020aa7c982000000b0052e2aa1a0fcsm7495234edt.77.2023.09.13.08.28.33 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Sep 2023 08:28:33 -0700 (PDT) From: Breno Leitao To: sdf@google.com, axboe@kernel.dk, asml.silence@gmail.com, willemdebruijn.kernel@gmail.com, kuba@kernel.org, pabeni@redhat.com, martin.lau@linux.dev, krisman@suse.de Cc: bpf@vger.kernel.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, io-uring@vger.kernel.org Subject: [PATCH v6 6/8] io_uring/cmd: Introduce SOCKET_URING_OP_GETSOCKOPT Date: Wed, 13 Sep 2023 08:27:42 -0700 Message-Id: <20230913152744.2333228-7-leitao@debian.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230913152744.2333228-1-leitao@debian.org> References: <20230913152744.2333228-1-leitao@debian.org> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Add support for getsockopt command (SOCKET_URING_OP_GETSOCKOPT), where level is SOL_SOCKET. This is similar to the getsockopt(2) system call, and both parameters are pointers to userspace. Important to say that userspace needs to keep the pointer alive until the CQE is completed. Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Breno Leitao --- include/uapi/linux/io_uring.h | 9 +++++++++ io_uring/uring_cmd.c | 15 +++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8e61f8b7c2ce..1c789ee6462d 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -43,6 +43,10 @@ struct io_uring_sqe { union { __u64 addr; /* pointer to buffer or iovecs */ __u64 splice_off_in; + struct { + __u32 level; + __u32 optname; + }; }; __u32 len; /* buffer size or number of iovecs */ union { @@ -89,6 +93,10 @@ struct io_uring_sqe { __u64 addr3; __u64 __pad2[1]; }; + struct { + __u64 optval; + __u64 optlen; + }; /* * If the ring is initialized with IORING_SETUP_SQE128, then * this field is used for 80 bytes of arbitrary command data @@ -734,6 +742,7 @@ struct io_uring_recvmsg_out { enum { SOCKET_URING_OP_SIOCINQ = 0, SOCKET_URING_OP_SIOCOUTQ, + SOCKET_URING_OP_GETSOCKOPT, }; #ifdef __cplusplus diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 5753c3611b74..a2a6ac0c503b 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -167,6 +167,19 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, } EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed); +static inline int io_uring_cmd_getsockopt(struct socket *sock, + struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + void __user *optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval)); + int __user *optlen = u64_to_user_ptr(READ_ONCE(cmd->sqe->optlen)); + bool compat = !!(issue_flags & IO_URING_F_COMPAT); + int optname = READ_ONCE(cmd->sqe->optname); + int level = READ_ONCE(cmd->sqe->level); + + return do_sock_getsockopt(sock, compat, level, optname, optval, optlen); +} + #if defined(CONFIG_NET) int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) { @@ -189,6 +202,8 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) if (ret) return ret; return arg; + case SOCKET_URING_OP_GETSOCKOPT: + return io_uring_cmd_getsockopt(sock, cmd, issue_flags); default: return -EOPNOTSUPP; } From patchwork Wed Sep 13 15:27:43 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Breno Leitao X-Patchwork-Id: 13383316 Received: from lindbergh.monkeyblade.net (lindbergh.monkeyblade.net [23.128.96.19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 774F0200CE; Wed, 13 Sep 2023 15:28:37 +0000 (UTC) Received: from mail-ej1-f48.google.com (mail-ej1-f48.google.com [209.85.218.48]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 982B71BFE; Wed, 13 Sep 2023 08:28:36 -0700 (PDT) Received: by mail-ej1-f48.google.com with SMTP id a640c23a62f3a-9ada6b0649fso89404266b.1; Wed, 13 Sep 2023 08:28:36 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1694618915; x=1695223715; 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=U2/uGjka4vxabDaOe18mLCK6HUraAejeoqQZCxCnFKY=; b=VfJSKC77ByBcDP5hwQNKU/LaZwJU8mhW2J4lGCflQxJPYPBlWv8MiUWM07pMeF2wNd imYd9kG5dFn/Lf7mka/dZ3KEm6lSVQAGB02YgPBle68EW5RHWzgArYNVQAtTW/jEWkXM BosC1Hztq8dQtrhNZgt828eA69e44l7VpJWko32kQ+ob058GwExIm6SDoqKWATVmRaGZ UKrSSDg/RL8eWx32NeMIUYBR2gn33WjeQhU/ms1mi+SqLVcH0+cyOqBQoWGawsrOSkXn hzHyING9VjwoB++ZbrrQt0cxEDKHQ8QWeDxJUn7m+OZ+URrv+KJ0c2dbJdUjstsc4hwM Iuag== X-Gm-Message-State: AOJu0YxN2qqEXXLVi6WWDSmv0En5elmsYUId1mLdbnrccbVTEG9TzYWt DnqR8Y5h79cpMEuXqEvNBuzL98F7oAM= X-Google-Smtp-Source: AGHT+IFPL0fdft0J2qmWcyGh3tAon9o5pRYXkFbBm4VNhe/VvDNL5sshV+GwHDo59c5fUujl0nGqDw== X-Received: by 2002:a17:906:1050:b0:9aa:17a2:e3fa with SMTP id j16-20020a170906105000b009aa17a2e3famr2523073ejj.72.1694618914957; Wed, 13 Sep 2023 08:28:34 -0700 (PDT) Received: from localhost (fwdproxy-cln-011.fbsv.net. [2a03:2880:31ff:b::face:b00c]) by smtp.gmail.com with ESMTPSA id l26-20020a1709061c5a00b009894b476310sm8516152ejg.163.2023.09.13.08.28.34 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Sep 2023 08:28:34 -0700 (PDT) From: Breno Leitao To: sdf@google.com, axboe@kernel.dk, asml.silence@gmail.com, willemdebruijn.kernel@gmail.com, kuba@kernel.org, pabeni@redhat.com, martin.lau@linux.dev, krisman@suse.de Cc: bpf@vger.kernel.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, io-uring@vger.kernel.org Subject: [PATCH v6 7/8] io_uring/cmd: Introduce SOCKET_URING_OP_SETSOCKOPT Date: Wed, 13 Sep 2023 08:27:43 -0700 Message-Id: <20230913152744.2333228-8-leitao@debian.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230913152744.2333228-1-leitao@debian.org> References: <20230913152744.2333228-1-leitao@debian.org> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Add support for SOCKET_URING_OP_SETSOCKOPT. This new command is similar to setsockopt(2). This implementation leverages the function do_sock_setsockopt(), which is shared with the setsockopt() system call path. Important to say that userspace needs to keep the pointer's memory alive until the operation is completed. I.e, the memory could not be deallocated before the CQE is returned to userspace. Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Breno Leitao --- include/uapi/linux/io_uring.h | 1 + io_uring/uring_cmd.c | 16 ++++++++++++++++ 2 files changed, 17 insertions(+) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 1c789ee6462d..99cdb2c1e240 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -743,6 +743,7 @@ enum { SOCKET_URING_OP_SIOCINQ = 0, SOCKET_URING_OP_SIOCOUTQ, SOCKET_URING_OP_GETSOCKOPT, + SOCKET_URING_OP_SETSOCKOPT, }; #ifdef __cplusplus diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index a2a6ac0c503b..2266c829d1c4 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -180,6 +180,20 @@ static inline int io_uring_cmd_getsockopt(struct socket *sock, return do_sock_getsockopt(sock, compat, level, optname, optval, optlen); } +static inline int io_uring_cmd_setsockopt(struct socket *sock, + struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + void __user *optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval)); + int optlen = READ_ONCE(cmd->sqe->optlen); + bool compat = !!(issue_flags & IO_URING_F_COMPAT); + int optname = READ_ONCE(cmd->sqe->optname); + int level = READ_ONCE(cmd->sqe->level); + + return do_sock_setsockopt(sock, compat, level, optname, optval, + optlen); +} + #if defined(CONFIG_NET) int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) { @@ -204,6 +218,8 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) return arg; case SOCKET_URING_OP_GETSOCKOPT: return io_uring_cmd_getsockopt(sock, cmd, issue_flags); + case SOCKET_URING_OP_SETSOCKOPT: + return io_uring_cmd_setsockopt(sock, cmd, issue_flags); default: return -EOPNOTSUPP; } From patchwork Wed Sep 13 15:27:44 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Breno Leitao X-Patchwork-Id: 13383317 X-Patchwork-Delegate: bpf@iogearbox.net Received: from lindbergh.monkeyblade.net (lindbergh.monkeyblade.net [23.128.96.19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 7471C1F925; Wed, 13 Sep 2023 15:28:40 +0000 (UTC) Received: from mail-ej1-f42.google.com (mail-ej1-f42.google.com [209.85.218.42]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id BE9A61BD6; Wed, 13 Sep 2023 08:28:39 -0700 (PDT) Received: by mail-ej1-f42.google.com with SMTP id a640c23a62f3a-99c3c8adb27so888272466b.1; Wed, 13 Sep 2023 08:28:39 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1694618918; x=1695223718; 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=f1vGDg0uCtdiqjKqDiwFtuGhRJ18xP0o/QuRB7i2CeI=; b=A11Q5a1VP/fcQ9TgOWN78oPoZg6kkmtsNi8QeNGpOkGuscvR8HqQ6es6BHcDKvKp2x lBr2okhW4SWaRc0xECzgePXGbkx53DUIerGucgd5ltRQdrnaZX1FW5qZwaDU3IgLEZ/5 tW3urGbcup0SaCqGrLa6idF3tGoqyRzxZ9eQoOCgzMuTThsnaf4rjR/FRMUDHAk1lj8/ qBHkYYbd95m76Pxyzal2pZKIzPqb0j/1E+u52NBGs9hULg8ElXMQwFfwZjuI0l0dcSLH FCMmdZpbvxuKPQboKGIqYdMMG2s5K7THQNlvjIVVXjnPxQaQPmGaxU+/xjplB5XwD3ZA noLw== X-Gm-Message-State: AOJu0YzCcGjpJd6aYMOGT5rgjkO0gH3gY+w4pBLs4Blmejm/B1PVWTYG iJKu5vdGCKZLxTCDtLkvzlo= X-Google-Smtp-Source: AGHT+IHmrrgmP8mf+1WIardtNbDBakZ+xUtLB1E1+f4WfhRclf5HQB29Q5O+QutRs462a3Yp0wPRsw== X-Received: by 2002:a17:906:3151:b0:9a1:c495:66bb with SMTP id e17-20020a170906315100b009a1c49566bbmr2361258eje.60.1694618918240; Wed, 13 Sep 2023 08:28:38 -0700 (PDT) Received: from localhost (fwdproxy-cln-009.fbsv.net. [2a03:2880:31ff:9::face:b00c]) by smtp.gmail.com with ESMTPSA id rn3-20020a170906d92300b0099cc3c7ace2sm8709378ejb.140.2023.09.13.08.28.37 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Sep 2023 08:28:37 -0700 (PDT) From: Breno Leitao To: sdf@google.com, axboe@kernel.dk, asml.silence@gmail.com, willemdebruijn.kernel@gmail.com, kuba@kernel.org, pabeni@redhat.com, martin.lau@linux.dev, krisman@suse.de, Andrii Nakryiko , Mykola Lysenko , Alexei Starovoitov , Daniel Borkmann , Song Liu , Yonghong Song , John Fastabend , KP Singh , Hao Luo , Jiri Olsa , Shuah Khan Cc: bpf@vger.kernel.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, io-uring@vger.kernel.org, =?utf-8?q?Daniel_M=C3=BCller?= , Wang Yufen , linux-kselftest@vger.kernel.org (open list:KERNEL SELFTEST FRAMEWORK) Subject: [PATCH v6 8/8] selftests/bpf/sockopt: Add io_uring support Date: Wed, 13 Sep 2023 08:27:44 -0700 Message-Id: <20230913152744.2333228-9-leitao@debian.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230913152744.2333228-1-leitao@debian.org> References: <20230913152744.2333228-1-leitao@debian.org> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Patchwork-Delegate: bpf@iogearbox.net Expand the BPF sockopt test to use also check for io_uring {g,s}etsockopt commands operations. Create infrastructure to run io_uring tests using the mini_liburing helpers, so, the {g,s}etsockopt operation could either be called from system calls, or, via io_uring. Add a 'use_io_uring' parameter to run_test(), to specify if the test should be run using io_uring if the parameter is set, or via the regular system calls if false. Call *all* tests twice, using the regular io_uring path, and the new io_uring path. Signed-off-by: Breno Leitao --- .../selftests/bpf/prog_tests/sockopt.c | 95 +++++++++++++++++-- 1 file changed, 89 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c index 9e6a5e3ed4de..40fb4c315ad9 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include "cgroup_helpers.h" static char bpf_log_buf[4096]; @@ -940,7 +941,85 @@ static int load_prog(const struct bpf_insn *insns, return fd; } -static int run_test(int cgroup_fd, struct sockopt_test *test) +/* Core function that handles io_uring ring initialization, + * sending SQE with sockopt command and waiting for the CQE. + */ +static int uring_sockopt(int op, int fd, int level, int optname, + const void *optval, socklen_t *optlen) +{ + struct io_uring_cqe *cqe; + struct io_uring_sqe *sqe; + struct io_uring ring; + int err; + + err = io_uring_queue_init(1, &ring, 0); + if (!ASSERT_OK(err, "Initialize io_uring ring")) + return err; + + sqe = io_uring_get_sqe(&ring); + if (!ASSERT_NEQ(sqe, NULL, "Get an SQE")) { + err = -1; + goto fail; + } + + if (op == SOCKET_URING_OP_GETSOCKOPT) + io_uring_prep_cmd_get(sqe, op, fd, level, optname, optval, + optlen); + else + io_uring_prep_cmd(sqe, op, fd, level, optname, optval, + *optlen); + + err = io_uring_submit(&ring); + if (!ASSERT_EQ(err, 1, "Submit SQE")) + goto fail; + + err = io_uring_wait_cqe(&ring, &cqe); + if (!ASSERT_OK(err, "Wait for CQE")) + goto fail; + + err = cqe->res; + +fail: + io_uring_queue_exit(&ring); + + return err; +} + +static int uring_setsockopt(int fd, int level, int optname, const void *optval, + socklen_t *optlen) +{ + return uring_sockopt(SOCKET_URING_OP_SETSOCKOPT, fd, level, optname, + optval, optlen); +} + +static int uring_getsockopt(int fd, int level, int optname, void *optval, + socklen_t *optlen) +{ + return uring_sockopt(SOCKET_URING_OP_GETSOCKOPT, fd, level, optname, + optval, optlen); +} + +/* Execute the setsocktopt operation */ +static int call_setsockopt(bool use_io_uring, int fd, int level, int optname, + const void *optval, socklen_t optlen) +{ + if (use_io_uring) + return uring_setsockopt(fd, level, optname, optval, &optlen); + + return setsockopt(fd, level, optname, optval, optlen); +} + +/* Execute the getsocktopt operation */ +static int call_getsockopt(bool use_io_uring, int fd, int level, int optname, + void *optval, socklen_t *optlen) +{ + if (use_io_uring) + return uring_getsockopt(fd, level, optname, optval, optlen); + + return getsockopt(fd, level, optname, optval, optlen); +} + +static int run_test(int cgroup_fd, struct sockopt_test *test, bool use_io_uring) { int sock_fd, err, prog_fd; void *optval = NULL; @@ -980,8 +1059,9 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) test->set_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder; } - err = setsockopt(sock_fd, test->set_level, test->set_optname, - test->set_optval, test->set_optlen); + err = call_setsockopt(use_io_uring, sock_fd, test->set_level, + test->set_optname, test->set_optval, + test->set_optlen); if (err) { if (errno == EPERM && test->error == EPERM_SETSOCKOPT) goto close_sock_fd; @@ -1008,8 +1088,8 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) socklen_t expected_get_optlen = test->get_optlen_ret ?: test->get_optlen; - err = getsockopt(sock_fd, test->get_level, test->get_optname, - optval, &optlen); + err = call_getsockopt(use_io_uring, sock_fd, test->get_level, + test->get_optname, optval, &optlen); if (err) { if (errno == EOPNOTSUPP && test->error == EOPNOTSUPP_GETSOCKOPT) goto free_optval; @@ -1063,7 +1143,10 @@ void test_sockopt(void) if (!test__start_subtest(tests[i].descr)) continue; - ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr); + ASSERT_OK(run_test(cgroup_fd, &tests[i], false), + tests[i].descr); + ASSERT_OK(run_test(cgroup_fd, &tests[i], true), + tests[i].descr); } close(cgroup_fd);