[PATCH v3 net-next 1/2] ibmvnic: Use atomic64_t for queue stats

[Mingming Cao <mmc@linux.ibm.com>]

This patch improves the ibmvnic driver by changing the per-queue
packet and byte counters to atomic64_t types. This makes updates
thread-safe and easier to manage across multiple cores.

It also updates the ethtool statistics to safely read these new counters.

Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Brian King <bjking1@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
Reviewed by: Rick Lindsley <ricklind@linux.ibm.com>
Reviewed by: Haren Myneni <haren@linux.ibm.com>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 42 ++++++++++++++++++------------
 drivers/net/ethernet/ibm/ibmvnic.h | 18 ++++++-------
 2 files changed, 34 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 92647e137cf8..79fdba4293a4 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2314,9 +2314,17 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter,
 		tx_buff = &tx_pool->tx_buff[index];
 		adapter->netdev->stats.tx_packets--;
 		adapter->netdev->stats.tx_bytes -= tx_buff->skb->len;
-		adapter->tx_stats_buffers[queue_num].batched_packets--;
-		adapter->tx_stats_buffers[queue_num].bytes -=
-						tx_buff->skb->len;
+		atomic64_dec(&adapter->tx_stats_buffers[queue_num].batched_packets);
+		if (atomic64_sub_return(tx_buff->skb->len,
+					&adapter->tx_stats_buffers[queue_num].bytes) < 0) {
+			atomic64_set(&adapter->tx_stats_buffers[queue_num].bytes, 0);
+			netdev_warn(adapter->netdev,
+				    "TX stats underflow on queue %u: bytes (%lld) < skb->len (%u),\n"
+				    "clamping to 0\n",
+				    queue_num,
+				    atomic64_read(&adapter->tx_stats_buffers[queue_num].bytes),
+				    tx_buff->skb->len);
+		}
 		dev_kfree_skb_any(tx_buff->skb);
 		tx_buff->skb = NULL;
 		adapter->netdev->stats.tx_dropped++;
@@ -2652,10 +2660,10 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	netdev->stats.tx_packets += tx_bpackets + tx_dpackets;
 	adapter->tx_send_failed += tx_send_failed;
 	adapter->tx_map_failed += tx_map_failed;
-	adapter->tx_stats_buffers[queue_num].batched_packets += tx_bpackets;
-	adapter->tx_stats_buffers[queue_num].direct_packets += tx_dpackets;
-	adapter->tx_stats_buffers[queue_num].bytes += tx_bytes;
-	adapter->tx_stats_buffers[queue_num].dropped_packets += tx_dropped;
+	atomic64_add(tx_bpackets, &adapter->tx_stats_buffers[queue_num].batched_packets);
+	atomic64_add(tx_dpackets, &adapter->tx_stats_buffers[queue_num].direct_packets);
+	atomic64_add(tx_bytes, &adapter->tx_stats_buffers[queue_num].bytes);
+	atomic64_add(tx_dropped, &adapter->tx_stats_buffers[queue_num].dropped_packets);
 
 	return ret;
 }
@@ -3569,8 +3577,8 @@ static int ibmvnic_poll(struct napi_struct *napi, int budget)
 		napi_gro_receive(napi, skb); /* send it up */
 		netdev->stats.rx_packets++;
 		netdev->stats.rx_bytes += length;
-		adapter->rx_stats_buffers[scrq_num].packets++;
-		adapter->rx_stats_buffers[scrq_num].bytes += length;
+		atomic64_inc(&adapter->rx_stats_buffers[scrq_num].packets);
+		atomic64_add(length, &adapter->rx_stats_buffers[scrq_num].bytes);
 		frames_processed++;
 	}
 
@@ -3874,22 +3882,22 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev,
 				      (adapter, ibmvnic_stats[i].offset));
 
 	for (j = 0; j < adapter->req_tx_queues; j++) {
-		data[i] = adapter->tx_stats_buffers[j].batched_packets;
+		data[i] = atomic64_read(&adapter->tx_stats_buffers[j].batched_packets);
 		i++;
-		data[i] = adapter->tx_stats_buffers[j].direct_packets;
+		data[i] = atomic64_read(&adapter->tx_stats_buffers[j].direct_packets);
 		i++;
-		data[i] = adapter->tx_stats_buffers[j].bytes;
+		data[i] = atomic64_read(&adapter->tx_stats_buffers[j].bytes);
 		i++;
-		data[i] = adapter->tx_stats_buffers[j].dropped_packets;
+		data[i] = atomic64_read(&adapter->tx_stats_buffers[j].dropped_packets);
 		i++;
 	}
 
 	for (j = 0; j < adapter->req_rx_queues; j++) {
-		data[i] = adapter->rx_stats_buffers[j].packets;
+		data[i] = atomic64_read(&adapter->rx_stats_buffers[j].packets);
 		i++;
-		data[i] = adapter->rx_stats_buffers[j].bytes;
+		data[i] = atomic64_read(&adapter->rx_stats_buffers[j].bytes);
 		i++;
-		data[i] = adapter->rx_stats_buffers[j].interrupts;
+		data[i] = atomic64_read(&adapter->rx_stats_buffers[j].interrupts);
 		i++;
 	}
 }
@@ -4307,7 +4315,7 @@ static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance)
 	if (unlikely(adapter->state != VNIC_OPEN))
 		return IRQ_NONE;
 
-	adapter->rx_stats_buffers[scrq->scrq_num].interrupts++;
+	atomic64_inc(&adapter->rx_stats_buffers[scrq->scrq_num].interrupts);
 
 	if (napi_schedule_prep(&adapter->napi[scrq->scrq_num])) {
 		disable_scrq_irq(adapter, scrq);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 246ddce753f9..e574eed97cc0 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -212,23 +212,23 @@ struct ibmvnic_statistics {
 } __packed __aligned(8);
 
 struct ibmvnic_tx_queue_stats {
-	u64 batched_packets;
-	u64 direct_packets;
-	u64 bytes;
-	u64 dropped_packets;
+	atomic64_t batched_packets;
+	atomic64_t direct_packets;
+	atomic64_t bytes;
+	atomic64_t dropped_packets;
 };
 
 #define NUM_TX_STATS \
-	(sizeof(struct ibmvnic_tx_queue_stats) / sizeof(u64))
+	(sizeof(struct ibmvnic_tx_queue_stats) / sizeof(atomic64_t))
 
 struct ibmvnic_rx_queue_stats {
-	u64 packets;
-	u64 bytes;
-	u64 interrupts;
+	atomic64_t packets;
+	atomic64_t bytes;
+	atomic64_t interrupts;
 };
 
 #define NUM_RX_STATS \
-	(sizeof(struct ibmvnic_rx_queue_stats) / sizeof(u64))
+	(sizeof(struct ibmvnic_rx_queue_stats) / sizeof(atomic64_t))
 
 struct ibmvnic_acl_buffer {
 	__be32 len;
-- 
2.39.3 (Apple Git-146)