[PATCH v1 net-next 14/14] net/sched: Make etf report drops on error_queue

[Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>]

Use the socket error queue for reporting dropped packets if the
socket has enabled that feature through the SO_TXTIME API.

Packets are dropped either on enqueue() if they aren't accepted by the
qdisc or on dequeue() if the system misses their deadline. Those are
reported as different errors so applications can react accordingly.

Userspace can retrieve the errors through the socket error queue and the
corresponding cmsg interfaces. A struct sock_extended_err* is used for
returning the error data, and the packet's timestamp can be retrieved by
adding both ee_data and ee_info fields as e.g.:

    ((__u64) serr->ee_data << 32) + serr->ee_info

This feature is disabled by default and must be explicitly enabled by
applications. Enabling it can bring some overhead for the Tx cycles
of the application.

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
 include/linux/socket.h        |  4 +++-
 include/net/sock.h            |  1 +
 include/uapi/linux/errqueue.h |  2 ++
 net/sched/sch_etf.c           | 37 +++++++++++++++++++++++++++++++++--
 4 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/include/linux/socket.h b/include/linux/socket.h
index ca476b7a8ff0..75e11d29b32a 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -85,7 +85,9 @@ struct cmsghdr {
 
 struct sock_txtime {
 	clockid_t	clockid;	/* reference clockid */
-	u16		flags;		/* bit 0: txtime in deadline_mode */
+	u16		flags;		/* bit 0: txtime in deadline_mode
+					 * bit 1: report drops on sk err queue
+					 */
 };
 
 /*
diff --git a/include/net/sock.h b/include/net/sock.h
index 73f4404e49e4..e681a45cfe7e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -473,6 +473,7 @@ struct sock {
 	u16			sk_clockid;
 	u16			sk_txtime_flags;
 #define SK_TXTIME_DEADLINE_MASK	BIT(0)
+#define SK_TXTIME_RECV_ERR_MASK	BIT(1)
 
 	struct socket		*sk_socket;
 	void			*sk_user_data;
diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h
index dc64cfaf13da..66fd5e443c94 100644
--- a/include/uapi/linux/errqueue.h
+++ b/include/uapi/linux/errqueue.h
@@ -25,6 +25,8 @@ struct sock_extended_err {
 #define SO_EE_OFFENDER(ee)	((struct sockaddr*)((ee)+1))
 
 #define SO_EE_CODE_ZEROCOPY_COPIED	1
+#define SO_EE_CODE_TXTIME_INVALID_PARAM	2
+#define SO_EE_CODE_TXTIME_MISSED	3
 
 /**
  *	struct scm_timestamping - timestamps exposed through cmsg
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index 5514a8aa3bd5..166f4b72875b 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/errno.h>
+#include <linux/errqueue.h>
 #include <linux/rbtree.h>
 #include <linux/skbuff.h>
 #include <linux/posix-timers.h>
@@ -124,6 +125,35 @@ static void reset_watchdog(struct Qdisc *sch)
 	qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next));
 }
 
+static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
+{
+	struct sock_exterr_skb *serr;
+	ktime_t txtime = skb->tstamp;
+
+	if (!skb->sk || !(skb->sk->sk_txtime_flags & SK_TXTIME_RECV_ERR_MASK))
+		return;
+
+	skb = skb_clone_sk(skb);
+	if (!skb)
+		return;
+
+	sock_hold(skb->sk);
+
+	serr = SKB_EXT_ERR(skb);
+	serr->ee.ee_errno = err;
+	serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL;
+	serr->ee.ee_type = 0;
+	serr->ee.ee_code = code;
+	serr->ee.ee_pad = 0;
+	serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */
+	serr->ee.ee_info = txtime; /* low part of tstamp */
+
+	if (sock_queue_err_skb(skb->sk, skb))
+		kfree_skb(skb);
+
+	sock_put(skb->sk);
+}
+
 static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
 				      struct sk_buff **to_free)
 {
@@ -131,8 +161,10 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
 	struct rb_node **p = &q->head.rb_node, *parent = NULL;
 	ktime_t txtime = nskb->tstamp;
 
-	if (!is_packet_valid(sch, nskb))
+	if (!is_packet_valid(sch, nskb)) {
+		report_sock_error(nskb, EINVAL, SO_EE_CODE_TXTIME_INVALID_PARAM);
 		return qdisc_drop(nskb, sch, to_free);
+	}
 
 	while (*p) {
 		struct sk_buff *skb;
@@ -175,6 +207,8 @@ static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb,
 	if (drop) {
 		struct sk_buff *to_free = NULL;
 
+		report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED);
+
 		qdisc_drop(skb, sch, &to_free);
 		kfree_skb_list(to_free);
 		qdisc_qstats_overlimit(sch);
@@ -200,7 +234,6 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
 	now = q->get_time();
 
 	/* Drop if packet has expired while in queue. */
-	/* FIXME: Must return error on the socket's error queue */
 	if (ktime_before(skb->tstamp, now)) {
 		timesortedlist_erase(sch, skb, true);
 		skb = NULL;
-- 
2.17.1