Received: by 2002:ad5:474a:0:0:0:0:0 with SMTP id i10csp851364imu; Fri, 11 Jan 2019 10:07:59 -0800 (PST) X-Google-Smtp-Source: ALg8bN5Q1v0RPR6hVZwreUGSxQGHyQ5hwW1KDif0uN49DigmApTvpCNakESOUVtv36uXqmpeMB/4 X-Received: by 2002:a63:ee0e:: with SMTP id e14mr14010479pgi.8.1547230078990; Fri, 11 Jan 2019 10:07:58 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1547230078; cv=none; d=google.com; s=arc-20160816; b=suTU9f/UBa5NzWpswKnrUvMK8bYEcP2F5lxvhfBmgo43jy7XLjNBTZT6P9hlRPcMVq aSaAElgxhXpy2jzjZRigoMTJyj6k9JCCIsQUJllOUYpKTzL5ojce48I/A2yLJ6Xw7mgV YgZoFmoXD7PbnC94RhfrNNMAL4ZZhctPeCkKIKdLCHZg4w7kt7q97bIT6spsusmnj9LI jLt66nlhw9zJnKDCkoKqVAy+k4HS1SWNxBhvgho1Jo3vw3A420at2cTXigIe1MVX9VNo OjblqzLkR3TFW3UG9f2pLxPn/pllJ3ePqs2nJYMUYptfv7sYtyOgrlBPcFXEacJi8ZWw TNgg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:content-transfer-encoding:mime-version :user-agent:references:in-reply-to:message-id:date:subject:cc:to :from:dkim-signature; bh=knG3+GkwZG4JfjcS3gt/mmoAG6kCXQc6anDbAOVP0dQ=; b=Mj+9pjHnowpBphLNxZ3+Pllx4javdZ8+DCDGWx5hDhxPaQ8nd/rFmE0GOW44VIAVPb Idp0doQaD/QJNHeZgYvuert2IMOSul68Ij6DWRDb2Tx06lr98SbKQGFd26EEQCiMo4vj utdtzNclcT0XaDB0THQ8jAsvz5jty9LFJ8Md9hAPstzu9ksEtIUNRLjITEdy9Ltc5zDW 33++LMdOQ5ciE6eglXs03icM5UjIPJYhUbk48KlWZS05yWcB+oHw3m0a2bhzalJ5xAMX 5ZWJVsJI1RuNSsbstpdnj1KRXfwM60WVF9yKq1UtPo81ixnsT4oOFm21IutRFCdybJdd zUjA== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@kernel.org header.s=default header.b=ZOjiOzqL; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id p12si13957189plk.77.2019.01.11.10.07.43; Fri, 11 Jan 2019 10:07:58 -0800 (PST) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; dkim=pass header.i=@kernel.org header.s=default header.b=ZOjiOzqL; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387862AbfAKORb (ORCPT + 99 others); Fri, 11 Jan 2019 09:17:31 -0500 Received: from mail.kernel.org ([198.145.29.99]:33878 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729564AbfAKOR3 (ORCPT ); Fri, 11 Jan 2019 09:17:29 -0500 Received: from localhost (5356596B.cm-6-7b.dynamic.ziggo.nl [83.86.89.107]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 1052E2177B; Fri, 11 Jan 2019 14:17:27 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1547216248; bh=+6geKQ4u97CWtjRpwfL1FFfxvLh+hwO0r9ItuB3xIXo=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=ZOjiOzqL2dPwQ1FAcmcjTK3o3ELFg5UQwCLR/eZVIgOFBTX6+O81paXSR1/rFptWm hgTt4GF8gDSkvcCDUDvqtU7Ry4RZResn3gmyZNWnbihUe2HHX8B75BuX26k8eIgDpa 8HXPnIP18aPyM+J+t1HfkXl9tEq0K+OFBd70Ktg0= From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Deepa Dinamani , "David S. Miller" Subject: [PATCH 4.4 29/88] sock: Make sock->sk_stamp thread-safe Date: Fri, 11 Jan 2019 15:07:58 +0100 Message-Id: <20190111131050.393667663@linuxfoundation.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190111131045.137499039@linuxfoundation.org> References: <20190111131045.137499039@linuxfoundation.org> User-Agent: quilt/0.65 X-stable: review X-Patchwork-Hint: ignore MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 4.4-stable review patch. If anyone has any objections, please let me know. ------------------ From: Deepa Dinamani [ Upstream commit 3a0ed3e9619738067214871e9cb826fa23b2ddb9 ] Al Viro mentioned (Message-ID <20170626041334.GZ10672@ZenIV.linux.org.uk>) that there is probably a race condition lurking in accesses of sk_stamp on 32-bit machines. sock->sk_stamp is of type ktime_t which is always an s64. On a 32 bit architecture, we might run into situations of unsafe access as the access to the field becomes non atomic. Use seqlocks for synchronization. This allows us to avoid using spinlocks for readers as readers do not need mutual exclusion. Another approach to solve this is to require sk_lock for all modifications of the timestamps. The current approach allows for timestamps to have their own lock: sk_stamp_lock. This allows for the patch to not compete with already existing critical sections, and side effects are limited to the paths in the patch. The addition of the new field maintains the data locality optimizations from commit 9115e8cd2a0c ("net: reorganize struct sock for better data locality") Note that all the instances of the sk_stamp accesses are either through the ioctl or the syscall recvmsg. Signed-off-by: Deepa Dinamani Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/sock.h | 36 ++++++++++++++++++++++++++++++++++-- net/compat.c | 15 +++++++++------ net/core/sock.c | 3 +++ net/sunrpc/svcsock.c | 2 +- 4 files changed, 47 insertions(+), 9 deletions(-) --- a/include/net/sock.h +++ b/include/net/sock.h @@ -299,6 +299,7 @@ struct cg_proto; * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received + * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING socket options * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_socket: Identd and reporting IO signals @@ -434,6 +435,9 @@ struct sock { long sk_sndtimeo; struct timer_list sk_timer; ktime_t sk_stamp; +#if BITS_PER_LONG==32 + seqlock_t sk_stamp_seq; +#endif u16 sk_tsflags; u32 sk_tskey; struct socket *sk_socket; @@ -2146,6 +2150,34 @@ static inline void sk_drops_add(struct s atomic_add(segs, &sk->sk_drops); } +static inline ktime_t sock_read_timestamp(struct sock *sk) +{ +#if BITS_PER_LONG==32 + unsigned int seq; + ktime_t kt; + + do { + seq = read_seqbegin(&sk->sk_stamp_seq); + kt = sk->sk_stamp; + } while (read_seqretry(&sk->sk_stamp_seq, seq)); + + return kt; +#else + return sk->sk_stamp; +#endif +} + +static inline void sock_write_timestamp(struct sock *sk, ktime_t kt) +{ +#if BITS_PER_LONG==32 + write_seqlock(&sk->sk_stamp_seq); + sk->sk_stamp = kt; + write_sequnlock(&sk->sk_stamp_seq); +#else + sk->sk_stamp = kt; +#endif +} + void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, @@ -2170,7 +2202,7 @@ sock_recv_timestamp(struct msghdr *msg, (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else - sk->sk_stamp = kt; + sock_write_timestamp(sk, kt); if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid) __sock_recv_wifi_status(msg, sk, skb); @@ -2190,7 +2222,7 @@ static inline void sock_recv_ts_and_drop if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY) __sock_recv_ts_and_drops(msg, sk, skb); else - sk->sk_stamp = skb->tstamp; + sock_write_timestamp(sk, skb->tstamp); } void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags); --- a/net/compat.c +++ b/net/compat.c @@ -443,12 +443,14 @@ int compat_sock_get_timestamp(struct soc err = -ENOENT; if (!sock_flag(sk, SOCK_TIMESTAMP)) sock_enable_timestamp(sk, SOCK_TIMESTAMP); - tv = ktime_to_timeval(sk->sk_stamp); + tv = ktime_to_timeval(sock_read_timestamp(sk)); + if (tv.tv_sec == -1) return err; if (tv.tv_sec == 0) { - sk->sk_stamp = ktime_get_real(); - tv = ktime_to_timeval(sk->sk_stamp); + ktime_t kt = ktime_get_real(); + sock_write_timestamp(sk, kt); + tv = ktime_to_timeval(kt); } err = 0; if (put_user(tv.tv_sec, &ctv->tv_sec) || @@ -471,12 +473,13 @@ int compat_sock_get_timestampns(struct s err = -ENOENT; if (!sock_flag(sk, SOCK_TIMESTAMP)) sock_enable_timestamp(sk, SOCK_TIMESTAMP); - ts = ktime_to_timespec(sk->sk_stamp); + ts = ktime_to_timespec(sock_read_timestamp(sk)); if (ts.tv_sec == -1) return err; if (ts.tv_sec == 0) { - sk->sk_stamp = ktime_get_real(); - ts = ktime_to_timespec(sk->sk_stamp); + ktime_t kt = ktime_get_real(); + sock_write_timestamp(sk, kt); + ts = ktime_to_timespec(kt); } err = 0; if (put_user(ts.tv_sec, &ctv->tv_sec) || --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2423,6 +2423,9 @@ void sock_init_data(struct socket *sock, sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_stamp = ktime_set(-1L, 0); +#if BITS_PER_LONG==32 + seqlock_init(&sk->sk_stamp_seq); +#endif #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -614,7 +614,7 @@ static int svc_udp_recvfrom(struct svc_r /* Don't enable netstamp, sunrpc doesn't need that much accuracy */ } - svsk->sk_sk->sk_stamp = skb->tstamp; + sock_write_timestamp(svsk->sk_sk, skb->tstamp); set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */ len = skb->len - sizeof(struct udphdr);