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>

8 files changed, 63 insertions, 0 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c1ef749b6f9f..f06ee8f91e74 100644
--- a/include/linux/netdevice.h
+++ b/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
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 83d5b3c2ac42..314be484c696 100644
--- a/include/net/inet_sock.h
+++ b/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 {
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 815b92a23936..7dc769e5452b 100644
--- a/include/net/pkt_sched.h
+++ b/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
diff --git a/include/net/sock.h b/include/net/sock.h
index 2ed99bfa4595..e0eac9ef44b5 100644
--- a/include/net/sock.h
+++ b/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;
 };
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 0ae758c90e54..a12692e5f7a8 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/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 */
diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h
index dc64cfaf13da..c0151200f7d1 100644
--- a/include/uapi/linux/errqueue.h
+++ b/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
  *
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index 4fe104b2411f..f8f4539f1135 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/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 */
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index bad3c03bcf43..949118461009 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/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