From patchwork Tue Jul 30 18:41:19 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Zijian Zhang X-Patchwork-Id: 13747775 X-Patchwork-Delegate: kuba@kernel.org Received: from mail-yb1-f172.google.com (mail-yb1-f172.google.com [209.85.219.172]) (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 5426B1AA3D9 for ; Tue, 30 Jul 2024 18:41:54 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.219.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1722364916; cv=none; b=V5IfQBw5K/vh+0bxXj/JQt2Ot8mjZtZC9LBDgl69BdYZKQ5w+LH9Gm0NJK+l4/88CPN5WDh77+qc0oQz/PiTFldhFFIkdo/8/DdLDS5kBa5JibaGRyXtCy5kZtsCjNLq5YBIO66r+5jU6Y1Mr6/J7cyt2APcJXC/I4WCW/KjYYI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1722364916; c=relaxed/simple; bh=dRcVp0Z7DoqqrWdM+KQxiL42PINqxpG662XC4ml1djE=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=Qs1JJ6xFTW9WVheqmG9V4co8PvShw4vT3lOLBgh7MCMIid4hUzDQikQqNyaQUgRI206BtWJlgBtWAq97iqr964z1wIJSj46SwdwUhCFXYJCDaRqGtwX5nfATPiPcHXkTMaKtG24VsLS1pKSSW/DM7KdXoKU+ibkALciUQrnruMM= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com; spf=pass smtp.mailfrom=bytedance.com; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b=azuwJn1D; arc=none smtp.client-ip=209.85.219.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=bytedance.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=bytedance.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=bytedance.com header.i=@bytedance.com header.b="azuwJn1D" Received: by mail-yb1-f172.google.com with SMTP id 3f1490d57ef6-dfef5980a69so3877254276.3 for ; Tue, 30 Jul 2024 11:41:54 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance.com; s=google; t=1722364913; x=1722969713; 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=rPnJjIq98SiA+JXhukXzURjAkFL/DxtFbjsUcIfNX/M=; b=azuwJn1DruXA7Z3idgopnUCvXwCiQkBpIVYex79mAflg36qoatXMT+BBcedHxltL9H DEqQByKt5NFTjm/mNC6l/3IyVsLJk50ijryFoGvmGLRhN7nKYleRBCF5coeYAEZDOklG k562fT6wYRcNEo/wTl+Itlpetx2aD3Y493d5ZKJNHgZLcgZnA2GAejq2yW2eCcf4kxn7 y1mjaCjNZiHKKebRHgf8IlV8umEHvUshGgSRuPHJrEfTT6CyaDZrsB8FZ9gxVd6XbFn+ DePdaJqzFhwaZByxSW+PanVwoOVmxfEBiDY7ZmnNFWkn7D967g0OocTg6+ml+8PlozM3 OBHQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1722364913; x=1722969713; 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=rPnJjIq98SiA+JXhukXzURjAkFL/DxtFbjsUcIfNX/M=; b=mOAQLTH8lOGc+Ng3qu1VjoRKIY0xkfdJr8SVuIs4cd152bh7tb+rTcKEJvcL9Mw9Ue JARVgnSpr7nFF0EWqkIXAnIxbQDKf3SgvfJ2WEtMc45TaNsHHU3zm7iBq4Qhk/cS851Y Z0k9To2Gn/pg9Wk8vFquTZkPlhPH27KOOyFFIpl0PIDMTVa8nfD3Jkh02DGrT85U/mBa xdxuFIaRWyyvwdE3OrpMiPJa8Ixoar0N/FuikphqvsMeH2CppPI603o9bgKUyZGDf5fi E2DCvVdyScalOg/Nv71J5VNVWatcbVsVU7srw2ZVF1vzZcDuH5/aMgmnjXZ/gllovlr7 wS7A== X-Gm-Message-State: AOJu0YwYTCl6th5aNhHsTpaUBhVXvQ2YOwlc5+A8U3LkfGB9zsJdYgGs dDNNxzfdxnmvnqWtxUpmQ+uIMJis+fWYQczlYSkrfS3Maev02EOl9B5+tw4QpjRc+xvl+C6JwbK v X-Google-Smtp-Source: AGHT+IEryLVpO7mWHAYjPE/Ggq/E9tDXYa/U1l8LGbTJENtvyJIBzIceolRcnGS9FGQKyr5d7l2SVw== X-Received: by 2002:a05:6902:1029:b0:e0b:4aa4:1704 with SMTP id 3f1490d57ef6-e0b5446cb77mr15436368276.18.1722364912943; Tue, 30 Jul 2024 11:41:52 -0700 (PDT) Received: from n191-036-066.byted.org ([139.177.233.173]) by smtp.gmail.com with ESMTPSA id 6a1803df08f44-6bb3fb07bf7sm66132716d6.137.2024.07.30.11.41.50 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 30 Jul 2024 11:41:52 -0700 (PDT) From: zijianzhang@bytedance.com To: netdev@vger.kernel.org Cc: linux-api@vger.kernel.org, willemdebruijn.kernel@gmail.com, almasrymina@google.com, edumazet@google.com, davem@davemloft.net, kuba@kernel.org, pabeni@redhat.com, dsahern@kernel.org, axboe@kernel.dk, shuah@kernel.org, linux-kselftest@vger.kernel.org, cong.wang@bytedance.com, xiaochun.lu@bytedance.com, Zijian Zhang Subject: [PATCH net-next v8 2/3] sock: add MSG_ZEROCOPY notification mechanism based on msg_control Date: Tue, 30 Jul 2024 18:41:19 +0000 Message-Id: <20240730184120.4089835-3-zijianzhang@bytedance.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20240730184120.4089835-1-zijianzhang@bytedance.com> References: <20240730184120.4089835-1-zijianzhang@bytedance.com> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Patchwork-Delegate: kuba@kernel.org From: Zijian Zhang The MSG_ZEROCOPY flag enables copy avoidance for socket send calls. However, zerocopy is not a free lunch. Apart from the management of user pages, the combination of poll + recvmsg to receive notifications incurs unignorable overhead in the applications. We try to mitigate this overhead with a new notification mechanism based on msg_control. Leveraging the general framework to copy cmsgs to the user space, we copy zerocopy notifications to the user upon returning of sendmsgs. Signed-off-by: Zijian Zhang Signed-off-by: Xiaochun Lu --- arch/alpha/include/uapi/asm/socket.h | 2 + arch/mips/include/uapi/asm/socket.h | 2 + arch/parisc/include/uapi/asm/socket.h | 2 + arch/sparc/include/uapi/asm/socket.h | 2 + include/linux/socket.h | 2 +- include/uapi/asm-generic/socket.h | 2 + include/uapi/linux/socket.h | 23 +++++++++ net/core/sock.c | 72 +++++++++++++++++++++++++-- 8 files changed, 102 insertions(+), 5 deletions(-) diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index e94f621903fe..7c32d9dbe47f 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -140,6 +140,8 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SCM_ZC_NOTIFICATION 78 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 60ebaed28a4c..3f7fade998cb 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -151,6 +151,8 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SCM_ZC_NOTIFICATION 78 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index be264c2b1a11..77f5bee0fdc9 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -132,6 +132,8 @@ #define SO_PASSPIDFD 0x404A #define SO_PEERPIDFD 0x404B +#define SCM_ZC_NOTIFICATION 0x404C + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 682da3714686..eb44fc515b45 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -133,6 +133,8 @@ #define SO_PASSPIDFD 0x0055 #define SO_PEERPIDFD 0x0056 +#define SCM_ZC_NOTIFICATION 0x0057 + #if !defined(__KERNEL__) diff --git a/include/linux/socket.h b/include/linux/socket.h index 40173c919d0f..71e3c6ebfed5 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -171,7 +171,7 @@ static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr static inline bool cmsg_copy_to_user(struct cmsghdr *__cmsg) { - return 0; + return __cmsg->cmsg_type == SCM_ZC_NOTIFICATION; } static inline size_t msg_data_left(struct msghdr *msg) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 8ce8a39a1e5f..02e9159c7944 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -135,6 +135,8 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SCM_ZC_NOTIFICATION 78 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index d3fcd3b5ec53..b5b5fa9febb1 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_SOCKET_H #define _UAPI_LINUX_SOCKET_H +#include + /* * Desired design of maximum size and alignment (see RFC2553) */ @@ -35,4 +37,25 @@ struct __kernel_sockaddr_storage { #define SOCK_TXREHASH_DISABLED 0 #define SOCK_TXREHASH_ENABLED 1 +#define ZC_NOTIFICATION_MAX 16 + +/* + * A zc_info_elem represents a completion notification for sendmsgs in range + * lo to high, zerocopy represents whether the underlying transmission is + * zerocopy or not. + */ +struct zc_info_elem { + __u32 lo; + __u32 hi; + __u8 zerocopy; +}; + +/* + * zc_info is the struct used for the SCM_ZC_NOTIFICATION control message. + */ +struct zc_info { + __u32 size; /* size of the zc_info_elem arr */ + struct zc_info_elem arr[]; +}; + #endif /* _UAPI_LINUX_SOCKET_H */ diff --git a/net/core/sock.c b/net/core/sock.c index b2cbe753af1d..37b1b12623ee 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1481,10 +1481,12 @@ int sk_setsockopt(struct sock *sk, int level, int optname, ret = -EOPNOTSUPP; } if (!ret) { - if (val < 0 || val > 1) + if (val < 0 || val > 1) { ret = -EINVAL; - else + } else { sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); + static_branch_enable(&tx_copy_cmsg_to_user_key); + } } break; @@ -2826,8 +2828,8 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, } EXPORT_SYMBOL(sock_alloc_send_pskb); -int __sock_cmsg_send(struct sock *sk, struct msghdr *msg __always_unused, - struct cmsghdr *cmsg, struct sockcm_cookie *sockc) +int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, + struct sockcm_cookie *sockc) { u32 tsflags; @@ -2863,6 +2865,68 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg __always_unused, case SCM_RIGHTS: case SCM_CREDENTIALS: break; + case SCM_ZC_NOTIFICATION: { + struct zc_info *zc = CMSG_DATA(cmsg); + struct sk_buff_head *q, local_q; + int cmsg_data_len, i = 0; + unsigned long flags; + struct sk_buff *skb; + + if (!sock_flag(sk, SOCK_ZEROCOPY) || sk->sk_family == PF_RDS) + return -EINVAL; + + cmsg_data_len = cmsg->cmsg_len - sizeof(struct cmsghdr); + if (cmsg_data_len < sizeof(struct zc_info)) + return -EINVAL; + + if (zc->size > ZC_NOTIFICATION_MAX || + (cmsg_data_len - sizeof(struct zc_info)) != + (zc->size * sizeof(struct zc_info_elem))) + return -EINVAL; + + q = &sk->sk_error_queue; + skb_queue_head_init(&local_q); + + /* Get zerocopy error messages from sk_error_queue, and add them + * to a local queue for later processing. This minimizes the + * code while the spinlock is held and irq is disabled. + */ + spin_lock_irqsave(&q->lock, flags); + skb = skb_peek(q); + while (skb && i < zc->size) { + struct sk_buff *skb_next = skb_peek_next(skb, q); + struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); + + if (serr->ee.ee_errno != 0 || + serr->ee.ee_origin != SO_EE_ORIGIN_ZEROCOPY) { + skb = skb_next; + continue; + } + + __skb_unlink(skb, q); + __skb_queue_tail(&local_q, skb); + skb = skb_next; + i++; + } + spin_unlock_irqrestore(&q->lock, flags); + + i = 0; + while ((skb = skb_peek(&local_q)) != NULL) { + struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); + + zc->arr[i].hi = serr->ee.ee_data; + zc->arr[i].lo = serr->ee.ee_info; + zc->arr[i].zerocopy = !(serr->ee.ee_code + & SO_EE_CODE_ZEROCOPY_COPIED); + __skb_unlink(skb, &local_q); + consume_skb(skb); + i++; + } + + zc->size = i; + msg->msg_control_copy_to_user = true; + break; + } default: return -EINVAL; }