Merge branch 'af_packet-timestamp'

Daniel Borkmann says:

====================
This is a joint effort with Willem to bring optional i) tx hw/sw
timestamping into PF_PACKET, that was reported by Paul Chavent,
and ii) to expose the type of timestamp to the user, which is in
the current situation not possible to distinguish with the RX_RING
and TX_RING API (but distinguishable through the normal timestamping
API), reported by Richard Cochran. This set is based on top of
``packet: account statistics only in tpacket_stats_u''. Related
discussion can be found in: http://patchwork.ozlabs.org/patch/238125/
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 65 insertions, 22 deletions

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 7e387ff64465..ba8309a3e01b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -339,6 +339,59 @@ static int __packet_get_status(struct packet_sock *po, void *frame)
 	}
 }
 
+static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec *ts,
+				   unsigned int flags)
+{
+	struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
+
+	if (shhwtstamps) {
+		if ((flags & SOF_TIMESTAMPING_SYS_HARDWARE) &&
+		    ktime_to_timespec_cond(shhwtstamps->syststamp, ts))
+			return TP_STATUS_TS_SYS_HARDWARE;
+		if ((flags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
+		    ktime_to_timespec_cond(shhwtstamps->hwtstamp, ts))
+			return TP_STATUS_TS_RAW_HARDWARE;
+	}
+
+	if (ktime_to_timespec_cond(skb->tstamp, ts))
+		return TP_STATUS_TS_SOFTWARE;
+
+	return 0;
+}
+
+static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame,
+				    struct sk_buff *skb)
+{
+	union tpacket_uhdr h;
+	struct timespec ts;
+	__u32 ts_status;
+
+	if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
+		return 0;
+
+	h.raw = frame;
+	switch (po->tp_version) {
+	case TPACKET_V1:
+		h.h1->tp_sec = ts.tv_sec;
+		h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC;
+		break;
+	case TPACKET_V2:
+		h.h2->tp_sec = ts.tv_sec;
+		h.h2->tp_nsec = ts.tv_nsec;
+		break;
+	case TPACKET_V3:
+	default:
+		WARN(1, "TPACKET version not supported.\n");
+		BUG();
+	}
+
+	/* one flush is safe, as both fields always lie on the same cacheline */
+	flush_dcache_page(pgv_to_page(&h.h1->tp_sec));
+	smp_wmb();
+
+	return ts_status;
+}
+
 static void *packet_lookup_frame(struct packet_sock *po,
 		struct packet_ring_buffer *rb,
 		unsigned int position,
@@ -1657,26 +1710,6 @@ drop:
 	return 0;
 }
 
-static void tpacket_get_timestamp(struct sk_buff *skb, struct timespec *ts,
-				  unsigned int flags)
-{
-	struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
-
-	if (shhwtstamps) {
-		if ((flags & SOF_TIMESTAMPING_SYS_HARDWARE) &&
-		    ktime_to_timespec_cond(shhwtstamps->syststamp, ts))
-			return;
-		if ((flags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
-		    ktime_to_timespec_cond(shhwtstamps->hwtstamp, ts))
-			return;
-	}
-
-	if (ktime_to_timespec_cond(skb->tstamp, ts))
-		return;
-
-	getnstimeofday(ts);
-}
-
 static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		       struct packet_type *pt, struct net_device *orig_dev)
 {
@@ -1691,6 +1724,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	unsigned short macoff, netoff, hdrlen;
 	struct sk_buff *copy_skb = NULL;
 	struct timespec ts;
+	__u32 ts_status;
 
 	if (skb->pkt_type == PACKET_LOOPBACK)
 		goto drop;
@@ -1773,7 +1807,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	spin_unlock(&sk->sk_receive_queue.lock);
 
 	skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
-	tpacket_get_timestamp(skb, &ts, po->tp_tstamp);
+
+	if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
+		getnstimeofday(&ts);
+
+	status |= ts_status;
 
 	switch (po->tp_version) {
 	case TPACKET_V1:
@@ -1874,10 +1912,14 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 	void *ph;
 
 	if (likely(po->tx_ring.pg_vec)) {
+		__u32 ts;
+
 		ph = skb_shinfo(skb)->destructor_arg;
 		BUG_ON(atomic_read(&po->tx_ring.pending) == 0);
 		atomic_dec(&po->tx_ring.pending);
-		__packet_set_status(po, ph, TP_STATUS_AVAILABLE);
+
+		ts = __packet_set_timestamp(po, ph, skb);
+		__packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts);
 	}
 
 	sock_wfree(skb);
@@ -1900,6 +1942,7 @@ 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;
+	sock_tx_timestamp(&po->sk, &skb_shinfo(skb)->tx_flags);
 	skb_shinfo(skb)->destructor_arg = ph.raw;
 
 	switch (po->tp_version) {