Merge tag 'v6.1-rc8' into rdma.git for-next

For dependencies in following patches

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

13 files changed, 109 insertions, 45 deletions

diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 560d1d442232..d3fdc290937f 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -1741,11 +1741,8 @@ static int e100_xmit_prepare(struct nic *nic, struct cb *cb,
 	dma_addr = dma_map_single(&nic->pdev->dev, skb->data, skb->len,
 				  DMA_TO_DEVICE);
 	/* If we can't map the skb, have the upper layer try later */
-	if (dma_mapping_error(&nic->pdev->dev, dma_addr)) {
-		dev_kfree_skb_any(skb);
-		skb = NULL;
+	if (dma_mapping_error(&nic->pdev->dev, dma_addr))
 		return -ENOMEM;
-	}
 
 	/*
 	 * Use the last 4 bytes of the SKB payload packet as the CRC, used for
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 4a6630586ec9..fc373472e4e1 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -32,6 +32,8 @@ struct workqueue_struct *fm10k_workqueue;
  **/
 static int __init fm10k_init_module(void)
 {
+	int ret;
+
 	pr_info("%s\n", fm10k_driver_string);
 	pr_info("%s\n", fm10k_copyright);
 
@@ -43,7 +45,13 @@ static int __init fm10k_init_module(void)
 
 	fm10k_dbg_init();
 
-	return fm10k_register_pci_driver();
+	ret = fm10k_register_pci_driver();
+	if (ret) {
+		fm10k_dbg_exit();
+		destroy_workqueue(fm10k_workqueue);
+	}
+
+	return ret;
 }
 module_init(fm10k_init_module);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b5dcd15ced36..b3cb587a2032 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -16644,6 +16644,8 @@ static struct pci_driver i40e_driver = {
  **/
 static int __init i40e_init_module(void)
 {
+	int err;
+
 	pr_info("%s: %s\n", i40e_driver_name, i40e_driver_string);
 	pr_info("%s: %s\n", i40e_driver_name, i40e_copyright);
 
@@ -16661,7 +16663,14 @@ static int __init i40e_init_module(void)
 	}
 
 	i40e_dbg_init();
-	return pci_register_driver(&i40e_driver);
+	err = pci_register_driver(&i40e_driver);
+	if (err) {
+		destroy_workqueue(i40e_wq);
+		i40e_dbg_exit();
+		return err;
+	}
+
+	return 0;
 }
 module_init(i40e_init_module);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 3f6187c16424..0d1bab4ac1b0 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -298,7 +298,6 @@ struct iavf_adapter {
 #define IAVF_FLAG_QUEUES_DISABLED		BIT(17)
 #define IAVF_FLAG_SETUP_NETDEV_FEATURES		BIT(18)
 #define IAVF_FLAG_REINIT_MSIX_NEEDED		BIT(20)
-#define IAVF_FLAG_INITIAL_MAC_SET		BIT(23)
 /* duplicates for common code */
 #define IAVF_FLAG_DCB_ENABLED			0
 	/* flags for admin queue service task */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 3fc572341781..f71e132ede09 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1087,12 +1087,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p)
 	if (ret)
 		return ret;
 
-	/* If this is an initial set MAC during VF spawn do not wait */
-	if (adapter->flags & IAVF_FLAG_INITIAL_MAC_SET) {
-		adapter->flags &= ~IAVF_FLAG_INITIAL_MAC_SET;
-		return 0;
-	}
-
 	ret = wait_event_interruptible_timeout(adapter->vc_waitqueue,
 					       iavf_is_mac_set_handled(netdev, addr->sa_data),
 					       msecs_to_jiffies(2500));
@@ -2605,8 +2599,6 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
 		ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr);
 	}
 
-	adapter->flags |= IAVF_FLAG_INITIAL_MAC_SET;
-
 	adapter->tx_desc_count = IAVF_DEFAULT_TXD;
 	adapter->rx_desc_count = IAVF_DEFAULT_RXD;
 	err = iavf_init_interrupt_scheme(adapter);
@@ -2921,7 +2913,6 @@ static void iavf_disable_vf(struct iavf_adapter *adapter)
 	iavf_free_queues(adapter);
 	memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE);
 	iavf_shutdown_adminq(&adapter->hw);
-	adapter->netdev->flags &= ~IFF_UP;
 	adapter->flags &= ~IAVF_FLAG_RESET_PENDING;
 	iavf_change_state(adapter, __IAVF_DOWN);
 	wake_up(&adapter->down_waitqueue);
@@ -3021,6 +3012,11 @@ static void iavf_reset_task(struct work_struct *work)
 		iavf_disable_vf(adapter);
 		mutex_unlock(&adapter->client_lock);
 		mutex_unlock(&adapter->crit_lock);
+		if (netif_running(netdev)) {
+			rtnl_lock();
+			dev_close(netdev);
+			rtnl_unlock();
+		}
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
 
@@ -3033,6 +3029,7 @@ continue_reset:
 
 	if (running) {
 		netif_carrier_off(netdev);
+		netif_tx_stop_all_queues(netdev);
 		adapter->link_up = false;
 		iavf_napi_disable_all(adapter);
 	}
@@ -3172,6 +3169,16 @@ reset_err:
 
 	mutex_unlock(&adapter->client_lock);
 	mutex_unlock(&adapter->crit_lock);
+
+	if (netif_running(netdev)) {
+		/* Close device to ensure that Tx queues will not be started
+		 * during netif_device_attach() at the end of the reset task.
+		 */
+		rtnl_lock();
+		dev_close(netdev);
+		rtnl_unlock();
+	}
+
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
 reset_finish:
 	rtnl_lock();
@@ -5035,23 +5042,21 @@ static int __maybe_unused iavf_resume(struct device *dev_d)
 static void iavf_remove(struct pci_dev *pdev)
 {
 	struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev);
-	struct net_device *netdev = adapter->netdev;
 	struct iavf_fdir_fltr *fdir, *fdirtmp;
 	struct iavf_vlan_filter *vlf, *vlftmp;
+	struct iavf_cloud_filter *cf, *cftmp;
 	struct iavf_adv_rss *rss, *rsstmp;
 	struct iavf_mac_filter *f, *ftmp;
-	struct iavf_cloud_filter *cf, *cftmp;
-	struct iavf_hw *hw = &adapter->hw;
+	struct net_device *netdev;
+	struct iavf_hw *hw;
 	int err;
 
-	/* When reboot/shutdown is in progress no need to do anything
-	 * as the adapter is already REMOVE state that was set during
-	 * iavf_shutdown() callback.
-	 */
-	if (adapter->state == __IAVF_REMOVE)
+	netdev = adapter->netdev;
+	hw = &adapter->hw;
+
+	if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
 		return;
 
-	set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section);
 	/* Wait until port initialization is complete.
 	 * There are flows where register/unregister netdev may race.
 	 */
@@ -5191,6 +5196,8 @@ static struct pci_driver iavf_driver = {
  **/
 static int __init iavf_init_module(void)
 {
+	int ret;
+
 	pr_info("iavf: %s\n", iavf_driver_string);
 
 	pr_info("%s\n", iavf_copyright);
@@ -5201,7 +5208,12 @@ static int __init iavf_init_module(void)
 		pr_err("%s: Failed to create workqueue\n", iavf_driver_name);
 		return -ENOMEM;
 	}
-	return pci_register_driver(&iavf_driver);
+
+	ret = pci_register_driver(&iavf_driver);
+	if (ret)
+		destroy_workqueue(iavf_wq);
+
+	return ret;
 }
 
 module_init(iavf_init_module);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 5a9e6563923e..24a701fd140e 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -2438,6 +2438,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		list_for_each_entry(f, &adapter->vlan_filter_list, list) {
 			if (f->is_new_vlan) {
 				f->is_new_vlan = false;
+				if (!f->vlan.vid)
+					continue;
 				if (f->vlan.tpid == ETH_P_8021Q)
 					set_bit(f->vlan.vid,
 						adapter->vsi.active_cvlans);
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 9e36f01dfa4f..e864634d66bc 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -958,7 +958,7 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 	 * associated to the queue to schedule NAPI handler
 	 */
 	q_vector = ring->q_vector;
-	if (q_vector)
+	if (q_vector && !(vsi->vf && ice_is_vf_disabled(vsi->vf)))
 		ice_trigger_sw_intr(hw, q_vector);
 
 	status = ice_dis_vsi_txq(vsi->port_info, txq_meta->vsi_idx,
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 938ba8c215cb..7276badfa19e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2240,6 +2240,31 @@ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_vsi_is_rx_queue_active
+ * @vsi: the VSI being configured
+ *
+ * Return true if at least one queue is active.
+ */
+bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	int i;
+
+	ice_for_each_rxq(vsi, i) {
+		u32 rx_reg;
+		int pf_q;
+
+		pf_q = vsi->rxq_map[i];
+		rx_reg = rd32(hw, QRX_CTRL(pf_q));
+		if (rx_reg & QRX_CTRL_QENA_STAT_M)
+			return true;
+	}
+
+	return false;
+}
+
+/**
  * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not
  * @vsi: VSI to check whether or not VLAN pruning is enabled.
  *
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index ec4bf0c89857..dcdf69a693e9 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -129,4 +129,5 @@ u16 ice_vsi_num_non_zero_vlans(struct ice_vsi *vsi);
 bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f);
 void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f);
 void ice_init_feature_support(struct ice_pf *pf);
+bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi);
 #endif /* !_ICE_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 0f6718719453..ca2898467dcb 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3145,15 +3145,15 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
  */
 static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data)
 {
-	irqreturn_t ret = IRQ_HANDLED;
 	struct ice_pf *pf = data;
-	bool irq_handled;
 
-	irq_handled = ice_ptp_process_ts(pf);
-	if (!irq_handled)
-		ret = IRQ_WAKE_THREAD;
+	if (ice_is_reset_in_progress(pf->state))
+		return IRQ_HANDLED;
 
-	return ret;
+	while (!ice_ptp_process_ts(pf))
+		usleep_range(50, 100);
+
+	return IRQ_HANDLED;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 011b727ab190..0f668468d141 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -614,11 +614,14 @@ static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64 in_tstamp)
  * 2) extend the 40b timestamp value to get a 64bit timestamp
  * 3) send that timestamp to the stack
  *
- * After looping, if we still have waiting SKBs, return true. This may cause us
- * effectively poll even when not strictly necessary. We do this because it's
- * possible a new timestamp was requested around the same time as the interrupt.
- * In some cases hardware might not interrupt us again when the timestamp is
- * captured.
+ * Returns true if all timestamps were handled, and false if any slots remain
+ * without a timestamp.
+ *
+ * After looping, if we still have waiting SKBs, return false. This may cause
+ * us effectively poll even when not strictly necessary. We do this because
+ * it's possible a new timestamp was requested around the same time as the
+ * interrupt. In some cases hardware might not interrupt us again when the
+ * timestamp is captured.
  *
  * Note that we only take the tracking lock when clearing the bit and when
  * checking if we need to re-queue this task. The only place where bits can be
@@ -641,7 +644,7 @@ static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx)
 	u8 idx;
 
 	if (!tx->init)
-		return false;
+		return true;
 
 	ptp_port = container_of(tx, struct ice_ptp_port, tx);
 	pf = ptp_port_to_pf(ptp_port);
@@ -2381,10 +2384,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb)
  */
 bool ice_ptp_process_ts(struct ice_pf *pf)
 {
-	if (pf->ptp.port.tx.init)
-		return ice_ptp_tx_tstamp(&pf->ptp.port.tx);
-
-	return false;
+	return ice_ptp_tx_tstamp(&pf->ptp.port.tx);
 }
 
 static void ice_ptp_periodic_work(struct kthread_work *work)
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index 0abeed092de1..1c51778db951 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -576,7 +576,10 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags)
 			return -EINVAL;
 		}
 		ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id);
-		ice_vsi_stop_all_rx_rings(vsi);
+
+		if (ice_vsi_is_rx_queue_active(vsi))
+			ice_vsi_stop_all_rx_rings(vsi);
+
 		dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n",
 			vf->vf_id);
 		return 0;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 99933e89717a..e338fa572793 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4869,6 +4869,8 @@ static struct pci_driver ixgbevf_driver = {
  **/
 static int __init ixgbevf_init_module(void)
 {
+	int err;
+
 	pr_info("%s\n", ixgbevf_driver_string);
 	pr_info("%s\n", ixgbevf_copyright);
 	ixgbevf_wq = create_singlethread_workqueue(ixgbevf_driver_name);
@@ -4877,7 +4879,13 @@ static int __init ixgbevf_init_module(void)
 		return -ENOMEM;
 	}
 
-	return pci_register_driver(&ixgbevf_driver);
+	err = pci_register_driver(&ixgbevf_driver);
+	if (err) {
+		destroy_workqueue(ixgbevf_wq);
+		return err;
+	}
+
+	return 0;
 }
 
 module_init(ixgbevf_init_module);