Merge branch 'Scheduled-packet-Transmission-ETF'

Jesus Sanchez-Palencia says:

====================
Scheduled packet Transmission: ETF

Changes since v1:
  - moved struct sock_txtime from socket.h to uapi net_tstamp.h;
  - sk_clockid was changed from u16 to u8;
  - sk_txtime_flags was changed from u16 to a u8 bit field in struct sock;
  - the socket option flags are now validated in sock_setsockopt();
  - added SO_EE_ORIGIN_TXTIME;
  - sockc.transmit_time is now initialized from all IPv4 Tx paths;
  - added support for the IPv6 Tx path;

Overview
========

This work consists of a set of kernel interfaces that can be used by
applications that require (time-based) Scheduled Tx of packets.
It is comprised by 3 new components to the kernel:

  - SO_TXTIME: socket option + cmsg programming interfaces.

  - etf: the "earliest txtime first" qdisc, that provides per-queue
	 TxTime-based scheduling. This has been renamed from 'tbs' to
	 'etf' to better describe its functionality.

  - taprio: the "time-aware priority scheduler" qdisc, that provides
	    per-port Time-Aware scheduling;

This patchset is providing the first 2 components, which have been
developed for longer. The taprio qdisc will be shared as an RFC separately
(shortly).

Note that this series is a follow up of the "Time based packet
transmission" RFCv3 [1].

etf (formerly known as 'tbs')
=============================

For applications/systems that the concept of time slices isn't precise
enough, the etf qdisc allows applications to control the instant when
a packet should leave the network controller. When used in conjunction
with taprio, it can also be used in case the application needs to
control with greater guarantee the offset into each time slice a packet
will be sent. Another use case of etf, is when only a small number of
applications on a system are time sensitive, so it can then be used
with a more traditional root qdisc (like mqprio).

The etf qdisc is designed so it buffers packets until a configurable
time before their deadline (Tx time). The qdisc uses a rbtree internally
so the buffered packets are always 'ordered' by their txtime (deadline)
and will be dequeued following the earliest txtime first.

It relies on the SO_TXTIME API set for receiving the per-packet timestamp
(txtime) as well as the config flags for each socket: the clockid to be
used as a reference, if the expected mode of txtime for that socket is
deadline or strict mode, and if packet drops should be reported on the
socket's error queue or not.

The qdisc will drop any packets with a Tx time in the past, or if a
packet expires while waiting for being dequeued. Drops can be reported
as errors back to userspace through the socket's error queue.

Example configuration:

$ tc qdisc add dev enp2s0 parent 100:1 etf offload delta 200000 \
            clockid CLOCK_TAI

Here, the Qdisc will use HW offload for the txtime control.
Packets will be dequeued by the qdisc "delta" (200000) nanoseconds before
their transmission time. Because this will be using HW offload and
since dynamic clocks are not supported by hrtimers, the system clock
and the PHC clock must be synchronized for this mode to behave as expected.

A more complete example can be found here, with instructions of how to
test it:

https://gist.github.com/jeez/bd3afeff081ba64a695008dd8215866f [2]

Note that we haven't modified the qdisc so it uses a timerqueue because
the modification needed was increasing the number of cachelines of a sk_buff.

This series is also hosted on github and can be found at [3].
The companion iproute2 patches can be found at [4].

[1] https://patchwork.ozlabs.org/cover/882342/

[2] github doesn't make it clear, but the gist can be cloned like this:
$ git clone https://gist.github.com/jeez/bd3afeff081ba64a695008dd8215866f scheduled-tx-tests

[3] https://github.com/jeez/linux/tree/etf-v2

[4] https://github.com/jeez/iproute2/tree/etf-v2
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/alpha/include/uapi/asm/socket.h

@@ -112,4 +112,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* _UAPI_ASM_SOCKET_H */

arch/ia64/include/uapi/asm/socket.h

@@ -114,4 +114,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* _ASM_IA64_SOCKET_H */

arch/mips/include/uapi/asm/socket.h

@@ -123,4 +123,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* _UAPI_ASM_SOCKET_H */

arch/parisc/include/uapi/asm/socket.h

@@ -104,4 +104,7 @@
 
 #define SO_ZEROCOPY		0x4035
 
+#define SO_TXTIME		0x4036
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* _UAPI_ASM_SOCKET_H */

arch/s390/include/uapi/asm/socket.h

@@ -111,4 +111,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* _ASM_SOCKET_H */

arch/sparc/include/uapi/asm/socket.h

@@ -101,6 +101,9 @@
 
 #define SO_ZEROCOPY		0x003e
 
+#define SO_TXTIME		0x003f
+#define SCM_TXTIME		SO_TXTIME
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002

arch/xtensa/include/uapi/asm/socket.h

@@ -116,4 +116,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif	/* _XTENSA_SOCKET_H */

drivers/net/ethernet/intel/igb/e1000_defines.h

@@ -1048,6 +1048,22 @@
 #define E1000_TQAVCTRL_XMIT_MODE	BIT(0)
 #define E1000_TQAVCTRL_DATAFETCHARB	BIT(4)
 #define E1000_TQAVCTRL_DATATRANARB	BIT(8)
+#define E1000_TQAVCTRL_DATATRANTIM	BIT(9)
+#define E1000_TQAVCTRL_SP_WAIT_SR	BIT(10)
+/* Fetch Time Delta - bits 31:16
+ *
+ * This field holds the value to be reduced from the launch time for
+ * fetch time decision. The FetchTimeDelta value is defined in 32 ns
+ * granularity.
+ *
+ * This field is 16 bits wide, and so the maximum value is:
+ *
+ * 65535 * 32 = 2097120 ~= 2.1 msec
+ *
+ * XXX: We are configuring the max value here since we couldn't come up
+ * with a reason for not doing so.
+ */
+#define E1000_TQAVCTRL_FETCHTIME_DELTA	(0xFFFF << 16)
 
 /* TX Qav Credit Control fields */
 #define E1000_TQAVCC_IDLESLOPE_MASK	0xFFFF

drivers/net/ethernet/intel/igb/igb.h

@@ -262,6 +262,7 @@ struct igb_ring {
 	u16 count;			/* number of desc. in the ring */
 	u8 queue_index;			/* logical index of the ring*/
 	u8 reg_idx;			/* physical index of the ring */
+	bool launchtime_enable;		/* true if LaunchTime is enabled */
 	bool cbs_enable;		/* indicates if CBS is enabled */
 	s32 idleslope;			/* idleSlope in kbps */
 	s32 sendslope;			/* sendSlope in kbps */

include/linux/netdevice.h

@@ -798,6 +798,7 @@ enum tc_setup_type {
 	TC_SETUP_QDISC_RED,
 	TC_SETUP_QDISC_PRIO,
 	TC_SETUP_QDISC_MQ,
+	TC_SETUP_QDISC_ETF,
 };
 
 /* These structures hold the attributes of bpf state that are being passed

include/net/inet_sock.h

@@ -148,6 +148,7 @@ struct inet_cork {
 	__s16			tos;
 	char			priority;
 	__u16			gso_size;
+	u64			transmit_time;
 };
 
 struct inet_cork_full {

include/net/pkt_sched.h

@@ -72,6 +72,8 @@ struct qdisc_watchdog {
 	struct Qdisc	*qdisc;
 };
 
+void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc,
+				 clockid_t clockid);
 void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc);
 void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires);
 
@@ -153,4 +155,9 @@ struct tc_cbs_qopt_offload {
 	s32 sendslope;
 };
 
+struct tc_etf_qopt_offload {
+	u8 enable;
+	s32 queue;
+};
+
 #endif

include/net/sock.h

@@ -319,6 +319,9 @@ struct sock_common {
   *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
   *	@sk_reuseport_cb: reuseport group container
   *	@sk_rcu: used during RCU grace period
+  *	@sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
+  *	@sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
+  *	@sk_txtime_unused: unused txtime flags
   */
 struct sock {
 	/*
@@ -475,6 +478,12 @@ struct sock {
 	u8			sk_shutdown;
 	u32			sk_tskey;
 	atomic_t		sk_zckey;
+
+	u8			sk_clockid;
+	u8			sk_txtime_deadline_mode : 1,
+				sk_txtime_report_errors : 1,
+				sk_txtime_unused : 6;
+
 	struct socket		*sk_socket;
 	void			*sk_user_data;
 #ifdef CONFIG_SECURITY
@@ -790,6 +799,7 @@ enum sock_flags {
 	SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
 	SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
 	SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */
+	SOCK_TXTIME,
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -1585,6 +1595,7 @@ void sock_kzfree_s(struct sock *sk, void *mem, int size);
 void sk_send_sigurg(struct sock *sk);
 
 struct sockcm_cookie {
+	u64 transmit_time;
 	u32 mark;
 	u16 tsflags;
 };

include/uapi/asm-generic/socket.h

@@ -107,4 +107,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* __ASM_GENERIC_SOCKET_H */

include/uapi/linux/errqueue.h

@@ -20,12 +20,16 @@ struct sock_extended_err {
 #define SO_EE_ORIGIN_ICMP6	3
 #define SO_EE_ORIGIN_TXSTATUS	4
 #define SO_EE_ORIGIN_ZEROCOPY	5
+#define SO_EE_ORIGIN_TXTIME	6
 #define SO_EE_ORIGIN_TIMESTAMPING SO_EE_ORIGIN_TXSTATUS
 
 #define SO_EE_OFFENDER(ee)	((struct sockaddr*)((ee)+1))
 
 #define SO_EE_CODE_ZEROCOPY_COPIED	1
 
+#define SO_EE_CODE_TXTIME_INVALID_PARAM	1
+#define SO_EE_CODE_TXTIME_MISSED	2
+
 /**
  *	struct scm_timestamping - timestamps exposed through cmsg
  *

include/uapi/linux/net_tstamp.h

@@ -141,4 +141,22 @@ struct scm_ts_pktinfo {
 	__u32 reserved[2];
 };
 
+/*
+ * SO_TXTIME gets a struct sock_txtime with flags being an integer bit
+ * field comprised of these values.
+ */
+enum txtime_flags {
+	SOF_TXTIME_DEADLINE_MODE = (1 << 0),
+	SOF_TXTIME_REPORT_ERRORS = (1 << 1),
+
+	SOF_TXTIME_FLAGS_LAST = SOF_TXTIME_REPORT_ERRORS,
+	SOF_TXTIME_FLAGS_MASK = (SOF_TXTIME_FLAGS_LAST - 1) |
+				 SOF_TXTIME_FLAGS_LAST
+};
+
+struct sock_txtime {
+	clockid_t       clockid;        /* reference clockid */
+	u32             flags;          /* flags defined by enum txtime_flags */
+};
+
 #endif /* _NET_TIMESTAMPING_H */

include/uapi/linux/pkt_sched.h

@@ -937,4 +937,22 @@ enum {
 
 #define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
 
+
+/* ETF */
+struct tc_etf_qopt {
+	__s32 delta;
+	__s32 clockid;
+	__u32 flags;
+#define TC_ETF_DEADLINE_MODE_ON	BIT(0)
+#define TC_ETF_OFFLOAD_ON	BIT(1)
+};
+
+enum {
+	TCA_ETF_UNSPEC,
+	TCA_ETF_PARMS,
+	__TCA_ETF_MAX,
+};
+
+#define TCA_ETF_MAX (__TCA_ETF_MAX - 1)
+
 #endif

net/core/skbuff.c

@@ -4898,7 +4898,6 @@ EXPORT_SYMBOL(skb_try_coalesce);
  */
 void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 {
-	skb->tstamp = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->skb_iif = 0;
 	skb->ignore_df = 0;
@@ -4912,6 +4911,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 
 	ipvs_reset(skb);
 	skb->mark = 0;
+	skb->tstamp = 0;
 }
 EXPORT_SYMBOL_GPL(skb_scrub_packet);
 

net/core/sock.c

@@ -91,6 +91,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <asm/unaligned.h>
 #include <linux/capability.h>
 #include <linux/errno.h>
 #include <linux/errqueue.h>
@@ -697,6 +698,7 @@ EXPORT_SYMBOL(sk_mc_loop);
 int sock_setsockopt(struct socket *sock, int level, int optname,
 		    char __user *optval, unsigned int optlen)
 {
+	struct sock_txtime sk_txtime;
 	struct sock *sk = sock->sk;
 	int val;
 	int valbool;
@@ -1070,6 +1072,26 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		}
 		break;
 
+	case SO_TXTIME:
+		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+			ret = -EPERM;
+		} else if (optlen != sizeof(struct sock_txtime)) {
+			ret = -EINVAL;
+		} else if (copy_from_user(&sk_txtime, optval,
+			   sizeof(struct sock_txtime))) {
+			ret = -EFAULT;
+		} else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) {
+			ret = -EINVAL;
+		} else {
+			sock_valbool_flag(sk, SOCK_TXTIME, true);
+			sk->sk_clockid = sk_txtime.clockid;
+			sk->sk_txtime_deadline_mode =
+				!!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE);
+			sk->sk_txtime_report_errors =
+				!!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS);
+		}
+		break;
+
 	default:
 		ret = -ENOPROTOOPT;
 		break;
@@ -1115,6 +1137,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		u64 val64;
 		struct linger ling;
 		struct timeval tm;
+		struct sock_txtime txtime;
 	} v;
 
 	int lv = sizeof(int);
@@ -1403,6 +1426,15 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sock_flag(sk, SOCK_ZEROCOPY);
 		break;
 
+	case SO_TXTIME:
+		lv = sizeof(v.txtime);
+		v.txtime.clockid = sk->sk_clockid;
+		v.txtime.flags |= sk->sk_txtime_deadline_mode ?
+				  SOF_TXTIME_DEADLINE_MODE : 0;
+		v.txtime.flags |= sk->sk_txtime_report_errors ?
+				  SOF_TXTIME_REPORT_ERRORS : 0;
+		break;
+
 	default:
 		/* We implement the SO_SNDLOWAT etc to not be settable
 		 * (1003.1g 7).
@@ -2137,6 +2169,13 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
 		sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK;
 		sockc->tsflags |= tsflags;
 		break;
+	case SCM_TXTIME:
+		if (!sock_flag(sk, SOCK_TXTIME))
+			return -EINVAL;
+		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64)))
+			return -EINVAL;
+		sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg));
+		break;
 	/* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */
 	case SCM_RIGHTS:
 	case SCM_CREDENTIALS:

net/ipv4/icmp.c

@@ -437,6 +437,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
+	ipc.sockc.transmit_time = 0;
 
 	if (icmp_param->replyopts.opt.opt.optlen) {
 		ipc.opt = &icmp_param->replyopts.opt;
@@ -715,6 +716,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
+	ipc.sockc.transmit_time = 0;
 
 	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
 			       type, code, &icmp_param);

net/ipv4/ip_output.c

@@ -1154,6 +1154,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	cork->tos = ipc->tos;
 	cork->priority = ipc->priority;
 	cork->tx_flags = ipc->tx_flags;
+	cork->transmit_time = ipc->sockc.transmit_time;
 
 	return 0;
 }
@@ -1414,6 +1415,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 
 	skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
 	skb->mark = sk->sk_mark;
+	skb->tstamp = cork->transmit_time;
 	/*
 	 * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
 	 * on dst refcount
@@ -1551,6 +1553,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
+	ipc.sockc.transmit_time = 0;
 
 	if (replyopts.opt.opt.optlen) {
 		ipc.opt = &replyopts.opt;

net/ipv4/ping.c

@@ -746,6 +746,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
+	ipc.sockc.transmit_time = 0;
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sk, msg, &ipc, false);

net/ipv4/raw.c

@@ -381,6 +381,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
+	skb->tstamp = sockc->transmit_time;
 	skb_dst_set(skb, &rt->dst);
 	*rtp = NULL;
 
@@ -562,6 +563,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	ipc.sockc.tsflags = sk->sk_tsflags;
+	ipc.sockc.transmit_time = 0;
 	ipc.addr = inet->inet_saddr;
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;

net/ipv4/udp.c

@@ -930,6 +930,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
+	ipc.sockc.transmit_time = 0;
 
 	getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
 

net/ipv6/ip6_output.c

@@ -1158,7 +1158,8 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 
 static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 			  struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6,
-			  struct rt6_info *rt, struct flowi6 *fl6)
+			  struct rt6_info *rt, struct flowi6 *fl6,
+			  const struct sockcm_cookie *sockc)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	unsigned int mtu;
@@ -1226,6 +1227,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 		cork->base.flags |= IPCORK_ALLFRAG;
 	cork->base.length = 0;
 
+	cork->base.transmit_time = sockc->transmit_time;
+
 	return 0;
 }
 
@@ -1575,7 +1578,7 @@ int ip6_append_data(struct sock *sk,
 		 * setup for corking
 		 */
 		err = ip6_setup_cork(sk, &inet->cork, &np->cork,
-				     ipc6, rt, fl6);
+				     ipc6, rt, fl6, sockc);
 		if (err)
 			return err;
 
@@ -1673,6 +1676,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
 
+	skb->tstamp = cork->base.transmit_time;
+
 	skb_dst_set(skb, dst_clone(&rt->dst));
 	IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
 	if (proto == IPPROTO_ICMPV6) {
@@ -1765,7 +1770,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 	cork->base.opt = NULL;
 	cork->base.dst = NULL;
 	v6_cork.opt = NULL;
-	err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6);
+	err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6, sockc);
 	if (err) {
 		ip6_cork_release(cork, &v6_cork);
 		return ERR_PTR(err);

net/ipv6/raw.c

@@ -620,7 +620,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 
 static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 			struct flowi6 *fl6, struct dst_entry **dstp,
-			unsigned int flags)
+			unsigned int flags, const struct sockcm_cookie *sockc)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net *net = sock_net(sk);
@@ -650,6 +650,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
+	skb->tstamp = sockc->transmit_time;
 	skb_dst_set(skb, &rt->dst);
 	*dstp = NULL;
 
@@ -848,6 +849,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 
 	sockc.tsflags = sk->sk_tsflags;
+	sockc.transmit_time = 0;
 	if (msg->msg_controllen) {
 		opt = &opt_space;
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
@@ -921,7 +923,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 back_from_confirm:
 	if (inet->hdrincl)
-		err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags);
+		err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst,
+					msg->msg_flags, &sockc);
 	else {
 		ipc6.opt = opt;
 		lock_sock(sk);

net/ipv6/udp.c

@@ -1148,6 +1148,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc6.dontfrag = -1;
 	ipc6.gso_size = up->gso_size;
 	sockc.tsflags = sk->sk_tsflags;
+	sockc.transmit_time = 0;
 
 	/* destination address check */
 	if (sin6) {

net/packet/af_packet.c

@@ -1951,6 +1951,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
 		goto out_unlock;
 	}
 
+	sockc.transmit_time = 0;
 	sockc.tsflags = sk->sk_tsflags;
 	if (msg->msg_controllen) {
 		err = sock_cmsg_send(sk, msg, &sockc);
@@ -1962,6 +1963,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
+	skb->tstamp = sockc.transmit_time;
 
 	sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags);
 
@@ -2457,6 +2459,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->dev = dev;
 	skb->priority = po->sk.sk_priority;
 	skb->mark = po->sk.sk_mark;
+	skb->tstamp = sockc->transmit_time;
 	sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
 	skb_shinfo(skb)->destructor_arg = ph.raw;
 
@@ -2633,6 +2636,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
+	sockc.transmit_time = 0;
 	sockc.tsflags = po->sk.sk_tsflags;
 	if (msg->msg_controllen) {
 		err = sock_cmsg_send(&po->sk, msg, &sockc);
@@ -2829,6 +2833,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_unlock;
 
+	sockc.transmit_time = 0;
 	sockc.tsflags = sk->sk_tsflags;
 	sockc.mark = sk->sk_mark;
 	if (msg->msg_controllen) {
@@ -2903,6 +2908,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
 	skb->mark = sockc.mark;
+	skb->tstamp = sockc.transmit_time;
 
 	if (has_vnet_hdr) {
 		err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());

net/sched/Kconfig

@@ -183,6 +183,17 @@ config NET_SCH_CBS
 	  To compile this code as a module, choose M here: the
 	  module will be called sch_cbs.
 
+config NET_SCH_ETF
+	tristate "Earliest TxTime First (ETF)"
+	help
+	  Say Y here if you want to use the Earliest TxTime First (ETF) packet
+	  scheduling algorithm.
+
+	  See the top of <file:net/sched/sch_etf.c> for more details.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called sch_etf.
+
 config NET_SCH_GRED
 	tristate "Generic Random Early Detection (GRED)"
 	---help---

net/sched/Makefile

@@ -54,6 +54,7 @@ obj-$(CONFIG_NET_SCH_FQ)	+= sch_fq.o
 obj-$(CONFIG_NET_SCH_HHF)	+= sch_hhf.o
 obj-$(CONFIG_NET_SCH_PIE)	+= sch_pie.o
 obj-$(CONFIG_NET_SCH_CBS)	+= sch_cbs.o
+obj-$(CONFIG_NET_SCH_ETF)	+= sch_etf.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o

net/sched/sch_api.c

@@ -596,12 +596,19 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
+void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc,
+				 clockid_t clockid)
 {
-	hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+	hrtimer_init(&wd->timer, clockid, HRTIMER_MODE_ABS_PINNED);
 	wd->timer.function = qdisc_watchdog;
 	wd->qdisc = qdisc;
 }
+EXPORT_SYMBOL(qdisc_watchdog_init_clockid);
+
+void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
+{
+	qdisc_watchdog_init_clockid(wd, qdisc, CLOCK_MONOTONIC);
+}
 EXPORT_SYMBOL(qdisc_watchdog_init);
 
 void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires)