1 files changed, 128 insertions, 62 deletions

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index cc8b13ebfa75..35f19430c84a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -80,14 +80,18 @@ static void ena_tx_timeout(struct net_device *dev)
 {
 	struct ena_adapter *adapter = netdev_priv(dev);
 
+	/* Change the state of the device to trigger reset
+	 * Check that we are not in the middle or a trigger already
+	 */
+
+	if (test_and_set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))
+		return;
+
 	u64_stats_update_begin(&adapter->syncp);
 	adapter->dev_stats.tx_timeout++;
 	u64_stats_update_end(&adapter->syncp);
 
 	netif_err(adapter, tx_err, dev, "Transmit time out\n");
-
-	/* Change the state of the device to trigger reset */
-	set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
 }
 
 static void update_rx_ring_mtu(struct ena_adapter *adapter, int mtu)
@@ -559,6 +563,7 @@ static void ena_free_all_rx_bufs(struct ena_adapter *adapter)
  */
 static void ena_free_tx_bufs(struct ena_ring *tx_ring)
 {
+	bool print_once = true;
 	u32 i;
 
 	for (i = 0; i < tx_ring->ring_size; i++) {
@@ -570,9 +575,16 @@ static void ena_free_tx_bufs(struct ena_ring *tx_ring)
 		if (!tx_info->skb)
 			continue;
 
-		netdev_notice(tx_ring->netdev,
-			      "free uncompleted tx skb qid %d idx 0x%x\n",
-			      tx_ring->qid, i);
+		if (print_once) {
+			netdev_notice(tx_ring->netdev,
+				      "free uncompleted tx skb qid %d idx 0x%x\n",
+				      tx_ring->qid, i);
+			print_once = false;
+		} else {
+			netdev_dbg(tx_ring->netdev,
+				   "free uncompleted tx skb qid %d idx 0x%x\n",
+				   tx_ring->qid, i);
+		}
 
 		ena_buf = tx_info->bufs;
 		dma_unmap_single(tx_ring->dev,
@@ -1109,7 +1121,8 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
 
 	tx_budget = tx_ring->ring_size / ENA_TX_POLL_BUDGET_DIVIDER;
 
-	if (!test_bit(ENA_FLAG_DEV_UP, &tx_ring->adapter->flags)) {
+	if (!test_bit(ENA_FLAG_DEV_UP, &tx_ring->adapter->flags) ||
+	    test_bit(ENA_FLAG_TRIGGER_RESET, &tx_ring->adapter->flags)) {
 		napi_complete_done(napi, 0);
 		return 0;
 	}
@@ -1117,26 +1130,40 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
 	tx_work_done = ena_clean_tx_irq(tx_ring, tx_budget);
 	rx_work_done = ena_clean_rx_irq(rx_ring, napi, budget);
 
-	if ((budget > rx_work_done) && (tx_budget > tx_work_done)) {
-		napi_complete_done(napi, rx_work_done);
+	/* If the device is about to reset or down, avoid unmask
+	 * the interrupt and return 0 so NAPI won't reschedule
+	 */
+	if (unlikely(!test_bit(ENA_FLAG_DEV_UP, &tx_ring->adapter->flags) ||
+		     test_bit(ENA_FLAG_TRIGGER_RESET, &tx_ring->adapter->flags))) {
+		napi_complete_done(napi, 0);
+		ret = 0;
 
+	} else if ((budget > rx_work_done) && (tx_budget > tx_work_done)) {
 		napi_comp_call = 1;
-		/* Tx and Rx share the same interrupt vector */
-		if (ena_com_get_adaptive_moderation_enabled(rx_ring->ena_dev))
-			ena_adjust_intr_moderation(rx_ring, tx_ring);
 
-		/* Update intr register: rx intr delay, tx intr delay and
-		 * interrupt unmask
+		/* Update numa and unmask the interrupt only when schedule
+		 * from the interrupt context (vs from sk_busy_loop)
 		 */
-		ena_com_update_intr_reg(&intr_reg,
-					rx_ring->smoothed_interval,
-					tx_ring->smoothed_interval,
-					true);
+		if (napi_complete_done(napi, rx_work_done)) {
+			/* Tx and Rx share the same interrupt vector */
+			if (ena_com_get_adaptive_moderation_enabled(rx_ring->ena_dev))
+				ena_adjust_intr_moderation(rx_ring, tx_ring);
+
+			/* Update intr register: rx intr delay,
+			 * tx intr delay and interrupt unmask
+			 */
+			ena_com_update_intr_reg(&intr_reg,
+						rx_ring->smoothed_interval,
+						tx_ring->smoothed_interval,
+						true);
+
+			/* It is a shared MSI-X.
+			 * Tx and Rx CQ have pointer to it.
+			 * So we use one of them to reach the intr reg
+			 */
+			ena_com_unmask_intr(rx_ring->ena_com_io_cq, &intr_reg);
+		}
 
-		/* It is a shared MSI-X. Tx and Rx CQ have pointer to it.
-		 * So we use one of them to reach the intr reg
-		 */
-		ena_com_unmask_intr(rx_ring->ena_com_io_cq, &intr_reg);
 
 		ena_update_ring_numa_node(tx_ring, rx_ring);
 
@@ -1698,12 +1725,22 @@ static void ena_down(struct ena_adapter *adapter)
 	adapter->dev_stats.interface_down++;
 	u64_stats_update_end(&adapter->syncp);
 
-	/* After this point the napi handler won't enable the tx queue */
-	ena_napi_disable_all(adapter);
 	netif_carrier_off(adapter->netdev);
 	netif_tx_disable(adapter->netdev);
 
+	/* After this point the napi handler won't enable the tx queue */
+	ena_napi_disable_all(adapter);
+
 	/* After destroy the queue there won't be any new interrupts */
+
+	if (test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags)) {
+		int rc;
+
+		rc = ena_com_dev_reset(adapter->ena_dev);
+		if (rc)
+			dev_err(&adapter->pdev->dev, "Device reset failed\n");
+	}
+
 	ena_destroy_all_io_queues(adapter);
 
 	ena_disable_io_intr_sync(adapter);
@@ -2065,6 +2102,14 @@ static void ena_netpoll(struct net_device *netdev)
 	struct ena_adapter *adapter = netdev_priv(netdev);
 	int i;
 
+	/* Dont schedule NAPI if the driver is in the middle of reset
+	 * or netdev is down.
+	 */
+
+	if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags) ||
+	    test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))
+		return;
+
 	for (i = 0; i < adapter->num_queues; i++)
 		napi_schedule(&adapter->ena_napi[i].napi);
 }
@@ -2165,32 +2210,50 @@ err:
 	ena_com_delete_debug_area(adapter->ena_dev);
 }
 
-static struct rtnl_link_stats64 *ena_get_stats64(struct net_device *netdev,
-						 struct rtnl_link_stats64 *stats)
+static void ena_get_stats64(struct net_device *netdev,
+			    struct rtnl_link_stats64 *stats)
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
-	struct ena_admin_basic_stats ena_stats;
-	int rc;
+	struct ena_ring *rx_ring, *tx_ring;
+	unsigned int start;
+	u64 rx_drops;
+	int i;
 
 	if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags))
-		return NULL;
+		return;
 
-	rc = ena_com_get_dev_basic_stats(adapter->ena_dev, &ena_stats);
-	if (rc)
-		return NULL;
+	for (i = 0; i < adapter->num_queues; i++) {
+		u64 bytes, packets;
 
-	stats->tx_bytes = ((u64)ena_stats.tx_bytes_high << 32) |
-		ena_stats.tx_bytes_low;
-	stats->rx_bytes = ((u64)ena_stats.rx_bytes_high << 32) |
-		ena_stats.rx_bytes_low;
+		tx_ring = &adapter->tx_ring[i];
 
-	stats->rx_packets = ((u64)ena_stats.rx_pkts_high << 32) |
-		ena_stats.rx_pkts_low;
-	stats->tx_packets = ((u64)ena_stats.tx_pkts_high << 32) |
-		ena_stats.tx_pkts_low;
+		do {
+			start = u64_stats_fetch_begin_irq(&tx_ring->syncp);
+			packets = tx_ring->tx_stats.cnt;
+			bytes = tx_ring->tx_stats.bytes;
+		} while (u64_stats_fetch_retry_irq(&tx_ring->syncp, start));
 
-	stats->rx_dropped = ((u64)ena_stats.rx_drops_high << 32) |
-		ena_stats.rx_drops_low;
+		stats->tx_packets += packets;
+		stats->tx_bytes += bytes;
+
+		rx_ring = &adapter->rx_ring[i];
+
+		do {
+			start = u64_stats_fetch_begin_irq(&rx_ring->syncp);
+			packets = rx_ring->rx_stats.cnt;
+			bytes = rx_ring->rx_stats.bytes;
+		} while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start));
+
+		stats->rx_packets += packets;
+		stats->rx_bytes += bytes;
+	}
+
+	do {
+		start = u64_stats_fetch_begin_irq(&adapter->syncp);
+		rx_drops = adapter->dev_stats.rx_drops;
+	} while (u64_stats_fetch_retry_irq(&adapter->syncp, start));
+
+	stats->rx_dropped = rx_drops;
 
 	stats->multicast = 0;
 	stats->collisions = 0;
@@ -2204,8 +2267,6 @@ static struct rtnl_link_stats64 *ena_get_stats64(struct net_device *netdev,
 
 	stats->rx_errors = 0;
 	stats->tx_errors = 0;
-
-	return stats;
 }
 
 static const struct net_device_ops ena_netdev_ops = {
@@ -2353,6 +2414,8 @@ static int ena_device_init(struct ena_com_dev *ena_dev, struct pci_dev *pdev,
 	 */
 	ena_com_set_admin_polling_mode(ena_dev, true);
 
+	ena_config_host_info(ena_dev);
+
 	/* Get Device Attributes*/
 	rc = ena_com_get_dev_attr_feat(ena_dev, get_feat_ctx);
 	if (rc) {
@@ -2377,11 +2440,10 @@ static int ena_device_init(struct ena_com_dev *ena_dev, struct pci_dev *pdev,
 
 	*wd_state = !!(aenq_groups & BIT(ENA_ADMIN_KEEP_ALIVE));
 
-	ena_config_host_info(ena_dev);
-
 	return 0;
 
 err_admin_init:
+	ena_com_delete_host_info(ena_dev);
 	ena_com_admin_destroy(ena_dev);
 err_mmio_read_less:
 	ena_com_mmio_reg_read_request_destroy(ena_dev);
@@ -2433,6 +2495,14 @@ static void ena_fw_reset_device(struct work_struct *work)
 	bool dev_up, wd_state;
 	int rc;
 
+	if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
+		dev_err(&pdev->dev,
+			"device reset schedule while reset bit is off\n");
+		return;
+	}
+
+	netif_carrier_off(netdev);
+
 	del_timer_sync(&adapter->timer_service);
 
 	rtnl_lock();
@@ -2446,12 +2516,6 @@ static void ena_fw_reset_device(struct work_struct *work)
 	 */
 	ena_close(netdev);
 
-	rc = ena_com_dev_reset(ena_dev);
-	if (rc) {
-		dev_err(&pdev->dev, "Device reset failed\n");
-		goto err;
-	}
-
 	ena_free_mgmnt_irq(adapter);
 
 	ena_disable_msix(adapter);
@@ -2464,6 +2528,8 @@ static void ena_fw_reset_device(struct work_struct *work)
 
 	ena_com_mmio_reg_read_request_destroy(ena_dev);
 
+	clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+
 	/* Finish with the destroy part. Start the init part */
 
 	rc = ena_device_init(ena_dev, adapter->pdev, &get_feat_ctx, &wd_state);
@@ -2509,6 +2575,8 @@ err_device_destroy:
 err:
 	rtnl_unlock();
 
+	clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags);
+
 	dev_err(&pdev->dev,
 		"Reset attempt failed. Can not reset the device\n");
 }
@@ -2527,6 +2595,9 @@ static void check_for_missing_tx_completions(struct ena_adapter *adapter)
 	if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags))
 		return;
 
+	if (test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))
+		return;
+
 	budget = ENA_MONITORED_TX_QUEUES;
 
 	for (i = adapter->last_monitored_tx_qid; i < adapter->num_queues; i++) {
@@ -2626,7 +2697,7 @@ static void ena_timer_service(unsigned long data)
 	if (host_info)
 		ena_update_host_info(host_info, adapter->netdev);
 
-	if (unlikely(test_and_clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
+	if (unlikely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
 		netif_err(adapter, drv, adapter->netdev,
 			  "Trigger reset is on\n");
 		ena_dump_stats_to_dmesg(adapter);
@@ -2660,7 +2731,7 @@ static int ena_calc_io_queue_num(struct pci_dev *pdev,
 		io_sq_num = get_feat_ctx->max_queues.max_sq_num;
 	}
 
-	io_queue_num = min_t(int, num_possible_cpus(), ENA_MAX_NUM_IO_QUEUES);
+	io_queue_num = min_t(int, num_online_cpus(), ENA_MAX_NUM_IO_QUEUES);
 	io_queue_num = min_t(int, io_queue_num, io_sq_num);
 	io_queue_num = min_t(int, io_queue_num,
 			     get_feat_ctx->max_queues.max_cq_num);
@@ -2722,7 +2793,6 @@ static void ena_set_dev_offloads(struct ena_com_dev_get_features_ctx *feat,
 	netdev->features =
 		dev_features |
 		NETIF_F_SG |
-		NETIF_F_NTUPLE |
 		NETIF_F_RXHASH |
 		NETIF_F_HIGHDMA;
 
@@ -3093,12 +3163,6 @@ static void ena_remove(struct pci_dev *pdev)
 	struct ena_com_dev *ena_dev;
 	struct net_device *netdev;
 
-	if (!adapter)
-		/* This device didn't load properly and it's resources
-		 * already released, nothing to do
-		 */
-		return;
-
 	ena_dev = adapter->ena_dev;
 	netdev = adapter->netdev;
 
@@ -3118,7 +3182,9 @@ static void ena_remove(struct pci_dev *pdev)
 
 	cancel_work_sync(&adapter->resume_io_task);
 
-	ena_com_dev_reset(ena_dev);
+	/* Reset the device only if the device is running. */
+	if (test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags))
+		ena_com_dev_reset(ena_dev);
 
 	ena_free_mgmnt_irq(adapter);