Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755920AbYLOO4f (ORCPT ); Mon, 15 Dec 2008 09:56:35 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754740AbYLOOzU (ORCPT ); Mon, 15 Dec 2008 09:55:20 -0500 Received: from mga09.intel.com ([134.134.136.24]:26559 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754123AbYLOOzL (ORCPT ); Mon, 15 Dec 2008 09:55:11 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.36,224,1228118400"; d="scan'208";a="370995459" From: Patrick Ohly To: linux-kernel@vger.kernel.org Cc: netdev@vger.kernel.org, David Miller , John Stultz , linux-api@vger.kernel.org, Patrick Ohly Subject: [RFC PATCH 03/12] net: socket infrastructure for SO_TIMESTAMPING Date: Mon, 15 Dec 2008 15:54:50 +0100 Message-Id: <1229352899-31330-4-git-send-email-patrick.ohly@intel.com> X-Mailer: git-send-email 1.6.0.4 In-Reply-To: <1229352899-31330-3-git-send-email-patrick.ohly@intel.com> References: <1229352899-31330-1-git-send-email-patrick.ohly@intel.com> <1229352899-31330-2-git-send-email-patrick.ohly@intel.com> <1229352899-31330-3-git-send-email-patrick.ohly@intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 13672 Lines: 410 The overlap with the old SO_TIMESTAMP[NS] options is handled so that time stamping in software (net_enable_timestamp()) is enabled when SO_TIMESTAMP[NS] and/or SO_TIMESTAMPING_RX_SOFTWARE is set. It's disabled if all of these are off. Signed-off-by: Patrick Ohly --- include/net/sock.h | 40 ++++++++++++++++++++++-- net/compat.c | 19 +++++++---- net/core/sock.c | 79 ++++++++++++++++++++++++++++++++++++++++------- net/socket.c | 86 ++++++++++++++++++++++++++++++++++++++++------------ 4 files changed, 182 insertions(+), 42 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 5a3a151..36807e4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -158,7 +158,7 @@ struct sock_common { * @sk_allocation: allocation mode * @sk_sndbuf: size of send buffer in bytes * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, - * %SO_OOBINLINE settings + * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) @@ -488,6 +488,13 @@ enum sock_flags { SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */ + SOCK_TIMESTAMPING_TX_HARDWARE, /* %SO_TIMESTAMPING %SOF_TIMESTAMPING_TX_HARDWARE */ + SOCK_TIMESTAMPING_TX_SOFTWARE, /* %SO_TIMESTAMPING %SOF_TIMESTAMPING_TX_SOFTWARE */ + SOCK_TIMESTAMPING_RX_HARDWARE, /* %SO_TIMESTAMPING %SOF_TIMESTAMPING_RX_HARDWARE */ + SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SO_TIMESTAMPING %SOF_TIMESTAMPING_RX_SOFTWARE */ + SOCK_TIMESTAMPING_SOFTWARE, /* %SO_TIMESTAMPING %SOF_TIMESTAMPING_SOFTWARE */ + SOCK_TIMESTAMPING_RAW_HARDWARE, /* %SO_TIMESTAMPING %SOF_TIMESTAMPING_RAW_HARDWARE */ + SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SO_TIMESTAMPING %SOF_TIMESTAMPING_SYS_HARDWARE */ }; static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) @@ -1342,13 +1349,40 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { ktime_t kt = skb->tstamp; - if (sock_flag(sk, SOCK_RCVTSTAMP)) + /* + * generate control messages if + * - receive time stamping in software requested (SOCK_RCVTSTAMP + * or SOCK_TIMESTAMPING_RX_SOFTWARE) + * - software time stamp available and wanted (SOCK_TIMESTAMPING_SOFTWARE) + * - hardware time stamps available and wanted (SOCK_TIMESTAMPING_SYS_HARDWARE + * or SOCK_TIMESTAMPING_RAW_HARDWARE) + */ + if (sock_flag(sk, SOCK_RCVTSTAMP) || + sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE) || + (kt.tv64 && sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) || + ((skb->optional & SKB_FLAGS_OPTIONAL_HWTSTAMPS) && + (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE) || + sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)))) __sock_recv_timestamp(msg, sk, skb); else sk->sk_stamp = kt; } /** + * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped + * @msg: outgoing packet + * @sk: socket sending this packet + * @shtx: filled with instructions for time stamping + * + * Currently only depends on SOCK_TIMESTAMPING* flags. Returns error code if + * parameters are invalid. + */ +extern int sock_tx_timestamp(struct msghdr *msg, + struct sock *sk, + union skb_shared_tx *shtx); + + +/** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from * @skb: socket buffer to eat @@ -1416,7 +1450,7 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb) return NULL; } -extern void sock_enable_timestamp(struct sock *sk); +extern void sock_enable_timestamp(struct sock *sk, int flag); extern int sock_get_timestamp(struct sock *, struct timeval __user *); extern int sock_get_timestampns(struct sock *, struct timespec __user *); diff --git a/net/compat.c b/net/compat.c index a3a2ba0..fb01ed9 100644 --- a/net/compat.c +++ b/net/compat.c @@ -216,7 +216,7 @@ Efault: int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *data) { struct compat_timeval ctv; - struct compat_timespec cts; + struct compat_timespec cts[3]; struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control; struct compat_cmsghdr cmhdr; int cmlen; @@ -233,12 +233,17 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat data = &ctv; len = sizeof(ctv); } - if (level == SOL_SOCKET && type == SCM_TIMESTAMPNS) { + if (level == SOL_SOCKET && + (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) { + int count = type == SCM_TIMESTAMPNS ? 1 : 3; + int i; struct timespec *ts = (struct timespec *)data; - cts.tv_sec = ts->tv_sec; - cts.tv_nsec = ts->tv_nsec; + for (i = 0; i < count; i++) { + cts[i].tv_sec = ts[i].tv_sec; + cts[i].tv_nsec = ts[i].tv_nsec; + } data = &cts; - len = sizeof(cts); + len = sizeof(cts[0]) * count; } cmlen = CMSG_COMPAT_LEN(len); @@ -455,7 +460,7 @@ int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) struct timeval tv; if (!sock_flag(sk, SOCK_TIMESTAMP)) - sock_enable_timestamp(sk); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); tv = ktime_to_timeval(sk->sk_stamp); if (tv.tv_sec == -1) return err; @@ -479,7 +484,7 @@ int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *usersta struct timespec ts; if (!sock_flag(sk, SOCK_TIMESTAMP)) - sock_enable_timestamp(sk); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); ts = ktime_to_timespec(sk->sk_stamp); if (ts.tv_sec == -1) return err; diff --git a/net/core/sock.c b/net/core/sock.c index ac4f0e7..35b4f4c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -120,6 +120,7 @@ #include #include #include +#include #include #include @@ -255,11 +256,14 @@ static void sock_warn_obsolete_bsdism(const char *name) } } -static void sock_disable_timestamp(struct sock *sk) +static void sock_disable_timestamp(struct sock *sk, int flag) { - if (sock_flag(sk, SOCK_TIMESTAMP)) { - sock_reset_flag(sk, SOCK_TIMESTAMP); - net_disable_timestamp(); + if (sock_flag(sk, flag)) { + sock_reset_flag(sk, flag); + if (!sock_flag(sk, SOCK_TIMESTAMP) && + !sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) { + net_disable_timestamp(); + } } } @@ -618,13 +622,36 @@ set_rcvbuf: else sock_set_flag(sk, SOCK_RCVTSTAMPNS); sock_set_flag(sk, SOCK_RCVTSTAMP); - sock_enable_timestamp(sk); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); } break; + case SO_TIMESTAMPING: + if (val & ~SOF_TIMESTAMPING_MASK) { + ret = EINVAL; + break; + } + sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE, + val & SOF_TIMESTAMPING_TX_HARDWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE, + val & SOF_TIMESTAMPING_TX_SOFTWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE, + val & SOF_TIMESTAMPING_RX_HARDWARE); + if (val & SOF_TIMESTAMPING_RX_SOFTWARE) + sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); + else + sock_disable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE, + val & SOF_TIMESTAMPING_SOFTWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE, + val & SOF_TIMESTAMPING_SYS_HARDWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE, + val & SOF_TIMESTAMPING_RAW_HARDWARE); + break; + case SO_RCVLOWAT: if (val < 0) val = INT_MAX; @@ -770,6 +797,24 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sock_flag(sk, SOCK_RCVTSTAMPNS); break; + case SO_TIMESTAMPING: + v.val = 0; + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE)) + v.val |= SOF_TIMESTAMPING_TX_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_TX_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE)) + v.val |= SOF_TIMESTAMPING_RX_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_RX_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE)) + v.val |= SOF_TIMESTAMPING_SYS_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) + v.val |= SOF_TIMESTAMPING_RAW_HARDWARE; + break; + case SO_RCVTIMEO: lv=sizeof(struct timeval); if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { @@ -971,7 +1016,8 @@ void sk_free(struct sock *sk) rcu_assign_pointer(sk->sk_filter, NULL); } - sock_disable_timestamp(sk); + sock_disable_timestamp(sk, SOCK_TIMESTAMP); + sock_disable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); if (atomic_read(&sk->sk_omem_alloc)) printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n", @@ -1789,7 +1835,7 @@ int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) { struct timeval tv; if (!sock_flag(sk, SOCK_TIMESTAMP)) - sock_enable_timestamp(sk); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); tv = ktime_to_timeval(sk->sk_stamp); if (tv.tv_sec == -1) return -ENOENT; @@ -1805,7 +1851,7 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) { struct timespec ts; if (!sock_flag(sk, SOCK_TIMESTAMP)) - sock_enable_timestamp(sk); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); ts = ktime_to_timespec(sk->sk_stamp); if (ts.tv_sec == -1) return -ENOENT; @@ -1817,11 +1863,20 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) } EXPORT_SYMBOL(sock_get_timestampns); -void sock_enable_timestamp(struct sock *sk) +void sock_enable_timestamp(struct sock *sk, int flag) { - if (!sock_flag(sk, SOCK_TIMESTAMP)) { - sock_set_flag(sk, SOCK_TIMESTAMP); - net_enable_timestamp(); + if (!sock_flag(sk, flag)) { + sock_set_flag(sk, flag); + /* + * we just set one of the two flags which require net + * time stamping, but time stamping might have been on + * already because of the other one + */ + if (!sock_flag(sk, + flag == SOCK_TIMESTAMP ? + SOCK_TIMESTAMPING_RX_SOFTWARE : + SOCK_TIMESTAMP)) + net_enable_timestamp(); } } diff --git a/net/socket.c b/net/socket.c index e9d65ea..669b739 100644 --- a/net/socket.c +++ b/net/socket.c @@ -545,6 +545,20 @@ void sock_release(struct socket *sock) sock->file = NULL; } +int sock_tx_timestamp(struct msghdr *msg, struct sock *sk, + union skb_shared_tx *shtx) +{ + shtx->flags = 0; + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE)) { + shtx->hardware = 1; + } + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE)) { + shtx->software = 1; + } + return 0; +} +EXPORT_SYMBOL(sock_tx_timestamp); + static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size) { @@ -595,33 +609,65 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, return result; } +static int ktime2ts(ktime_t kt, struct timespec *ts) +{ + if (kt.tv64) { + *ts = ktime_to_timespec(kt); + return 1; + } else { + return 0; + } +} + /* * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP) */ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { - ktime_t kt = skb->tstamp; - - if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { - struct timeval tv; - /* Race occurred between timestamp enabling and packet - receiving. Fill in the current time for now. */ - if (kt.tv64 == 0) - kt = ktime_get_real(); - skb->tstamp = kt; - tv = ktime_to_timeval(kt); - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, sizeof(tv), &tv); - } else { - struct timespec ts; - /* Race occurred between timestamp enabling and packet - receiving. Fill in the current time for now. */ - if (kt.tv64 == 0) - kt = ktime_get_real(); - skb->tstamp = kt; - ts = ktime_to_timespec(kt); - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, sizeof(ts), &ts); + int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); + struct timespec ts[3]; + int empty = 1; + struct skb_shared_hwtstamps *shhwtstamps = + skb_hwtstamps(skb); + + /* Race occurred between timestamp enabling and packet + receiving. Fill in the current time for now. */ + if (need_software_tstamp && skb->tstamp.tv64 == 0) + __net_timestamp(skb); + + if (need_software_tstamp) { + if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { + struct timeval tv; + skb_get_timestamp(skb, &tv); + put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, + sizeof(tv), &tv); + } else { + struct timespec ts; + skb_get_timestampns(skb, &ts); + put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, + sizeof(ts), &ts); + } + } + + + memset(ts, 0, sizeof(ts)); + if (skb->tstamp.tv64 && + sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) { + skb_get_timestampns(skb, ts + 0); + empty = 0; + } + if (shhwtstamps) { + if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE) && + ktime2ts(shhwtstamps->syststamp, ts + 1)) + empty = 0; + if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE) && + ktime2ts(shhwtstamps->hwtstamp, ts + 2)) + empty = 0; } + if (!empty) + put_cmsg(msg, SOL_SOCKET, + SCM_TIMESTAMPING, sizeof(ts), &ts); } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); -- 1.5.5.3 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/