NIU: Implement discard counters

Implementing discard counters for the NIU driver turned out to be more
complicated than first assumed.

The discard counters for the NIU neptune chip are only 16-bit (even
though this is a 64-bit chip).  These 16-bit counters can overflow
quickly, especially considering this is a 10Gbit/s ethernet card.

The overflow indication bit is, unfortunatly, not usable as the
counter value does not wrap, but remains at max value 0xFFFF.
Resulting in lost counts until the counter is reset.

The read and reset scheme also poses a problem. Both in theory and in
practice counters can be lost in between reading nr64() and clearing
the counter nw64().  For this reason, the number of counter clearings
nw64() is limited/reduced.  On the fast-path the counters are only
syncronized once it exceeds 0x7FFF.  When read by userspace, its
syncronized fully.

Signed-off-by: Jesper Dangaard Brouer <hawk@comx.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/niu.c

@@ -3527,6 +3527,51 @@ out:
 	}
 }
 
+static inline void niu_sync_rx_discard_stats(struct niu *np,
+					     struct rx_ring_info *rp,
+					     const int limit)
+{
+	/* This elaborate scheme is needed for reading the RX discard
+	 * counters, as they are only 16-bit and can overflow quickly,
+	 * and because the overflow indication bit is not usable as
+	 * the counter value does not wrap, but remains at max value
+	 * 0xFFFF.
+	 *
+	 * In theory and in practice counters can be lost in between
+	 * reading nr64() and clearing the counter nw64().  For this
+	 * reason, the number of counter clearings nw64() is
+	 * limited/reduced though the limit parameter.
+	 */
+	int rx_channel = rp->rx_channel;
+	u32 misc, wred;
+
+	/* RXMISC (Receive Miscellaneous Discard Count), covers the
+	 * following discard events: IPP (Input Port Process),
+	 * FFLP/TCAM, Full RCR (Receive Completion Ring) RBR (Receive
+	 * Block Ring) prefetch buffer is empty.
+	 */
+	misc = nr64(RXMISC(rx_channel));
+	if (unlikely((misc & RXMISC_COUNT) > limit)) {
+		nw64(RXMISC(rx_channel), 0);
+		rp->rx_errors += misc & RXMISC_COUNT;
+
+		if (unlikely(misc & RXMISC_OFLOW))
+			dev_err(np->device, "rx-%d: Counter overflow "
+				"RXMISC discard\n", rx_channel);
+	}
+
+	/* WRED (Weighted Random Early Discard) by hardware */
+	wred = nr64(RED_DIS_CNT(rx_channel));
+	if (unlikely((wred & RED_DIS_CNT_COUNT) > limit)) {
+		nw64(RED_DIS_CNT(rx_channel), 0);
+		rp->rx_dropped += wred & RED_DIS_CNT_COUNT;
+
+		if (unlikely(wred & RED_DIS_CNT_OFLOW))
+			dev_err(np->device, "rx-%d: Counter overflow "
+				"WRED discard\n", rx_channel);
+	}
+}
+
 static int niu_rx_work(struct niu *np, struct rx_ring_info *rp, int budget)
 {
 	int qlen, rcr_done = 0, work_done = 0;
@@ -3567,6 +3612,8 @@ static int niu_rx_work(struct niu *np, struct rx_ring_info *rp, int budget)
 
 	nw64(RX_DMA_CTL_STAT(rp->rx_channel), stat);
 
+	niu_sync_rx_discard_stats(np, rp, 0x7FFF);
+
 	return work_done;
 }
 
@@ -6073,6 +6120,8 @@ static void niu_get_rx_stats(struct niu *np)
 	for (i = 0; i < np->num_rx_rings; i++) {
 		struct rx_ring_info *rp = &np->rx_rings[i];
 
+		niu_sync_rx_discard_stats(np, rp, 0);
+
 		pkts += rp->rx_packets;
 		bytes += rp->rx_bytes;
 		dropped += rp->rx_dropped;
@@ -7014,6 +7063,8 @@ static void niu_get_ethtool_stats(struct net_device *dev,
 	for (i = 0; i < np->num_rx_rings; i++) {
 		struct rx_ring_info *rp = &np->rx_rings[i];
 
+		niu_sync_rx_discard_stats(np, rp, 0);
+
 		data[0] = rp->rx_channel;
 		data[1] = rp->rx_packets;
 		data[2] = rp->rx_bytes;