[PATCH net v6 1/2] enic: retain admin-channel DMA until queues stop

@@ -238,6 +238,12 @@ enum enic_vf_type {
 	ENIC_VF_TYPE_V2,
 };
 
+enum enic_admin_chan_state {
+	ENIC_ADMIN_CHAN_DOWN,
+	ENIC_ADMIN_CHAN_LIVE,
+	ENIC_ADMIN_CHAN_QUARANTINED,
+};
+
 /* Per-instance private data structure */
 struct enic {
 	struct net_device *netdev;

@@ -298,12 +304,9 @@ struct enic {
 
 	/* Admin channel resources for SR-IOV MBOX */
 	bool has_admin_channel;
-	/* true only while the admin WQ/RQ/CQ are allocated and enabled; gates
-	 * enic_admin_channel_close() so it is a no-op after a failed (re)open
-	 * left the resources freed.
-	 */
-	bool admin_chan_up;
-	/* set on send timeout; cleared on channel re-open */
+	/* QUARANTINED retains admin DMA until a final teardown recheck. */
+	enum enic_admin_chan_state admin_chan_state;
+	/* Blocks sends throughout close, partial open and timeout recovery. */
 	bool mbox_send_disabled;
 	struct vnic_wq admin_wq;
 	struct vnic_rq admin_rq;

@@ -5,6 +5,7 @@
 #include <linux/netdevice.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
+#include <linux/iopoll.h>
 
 #include "vnic_dev.h"
 #include "vnic_wq.h"

@@ -530,11 +531,17 @@ static void enic_admin_msg_drain(struct enic *enic)
 
 int enic_admin_channel_open(struct enic *enic)
 {
+	int close_err;
 	int err;
 
 	if (!enic->has_admin_channel)
 		return -ENODEV;
-
+	if (READ_ONCE(enic->admin_chan_state) != ENIC_ADMIN_CHAN_DOWN) {
+		netdev_err(enic->netdev,
+			   "Refusing to open non-down admin channel (%u)\n",
+			   READ_ONCE(enic->admin_chan_state));
+		return -EBUSY;
+	}
 	/* Keep MBOX sends disabled for the entire open sequence.  It is
 	 * cleared only after every resource is allocated and enabled below,
 	 * so any early error return here leaves sends disabled and a

@@ -567,6 +574,7 @@ int enic_admin_channel_open(struct enic *enic)
 
 	vnic_wq_enable(&enic->admin_wq);
 	vnic_rq_enable(&enic->admin_rq);
+	WRITE_ONCE(enic->admin_chan_state, ENIC_ADMIN_CHAN_LIVE);
 
 	err = enic_admin_rq_fill(enic, GFP_KERNEL);
 	if (err) {

@@ -600,60 +608,51 @@ int enic_admin_channel_open(struct enic *enic)
 		   enic->admin_cq[0].last_color,
 		   enic->admin_cq[1].last_color);
 
-	enic->admin_chan_up = true;
-
 	return 0;
 
 disable_queues:
-	enic_admin_teardown_intr(enic);
-	enic_admin_qp_type_set(enic, QP_DISABLE);
-	if (vnic_wq_disable(&enic->admin_wq))
-		netdev_warn(enic->netdev, "Failed to disable admin WQ\n");
-	if (vnic_rq_disable(&enic->admin_rq))
-		netdev_warn(enic->netdev, "Failed to disable admin RQ\n");
-	cancel_work_sync(&enic->admin_msg_work);
-	enic_admin_msg_drain(enic);
-	enic_admin_rq_drain(enic);
+	close_err = enic_admin_channel_close(enic);
+	if (close_err)
+		netdev_err(enic->netdev,
+			   "Failed to close partial admin channel: %d\n",
+			   close_err);
+	return err;
 free_resources:
 	enic_admin_free_resources(enic);
 	return err;
 }
 
-void enic_admin_channel_close(struct enic *enic)
+static int enic_admin_wq_disable(struct enic *enic)
 {
-	int err;
+	struct vnic_wq *wq = &enic->admin_wq;
+	u32 running;
 
-	if (!enic->has_admin_channel)
-		return;
-
-	/* Nothing to tear down if the channel was never (re)opened, e.g. a
-	 * failed enic_admin_channel_open() in probe or in the reset path;
-	 * otherwise the disable/clean calls below dereference freed resources.
-	 */
-	if (!enic->admin_chan_up)
-		return;
-
-	WRITE_ONCE(enic->mbox_send_disabled, true);
-
-	netdev_dbg(enic->netdev, "admin channel close\n");
+	iowrite32(0, &wq->ctrl->enable);
+	return read_poll_timeout(ioread32, running, !running, 10, 500000,
+				 false, &wq->ctrl->running);
+}
 
-	vnic_intr_mask(&enic->admin_intr);
-	enic_admin_teardown_intr(enic);
-	cancel_work_sync(&enic->link_notify_work);
-	cancel_work_sync(&enic->admin_msg_work);
-	enic_admin_msg_drain(enic);
+static int enic_admin_rq_disable(struct enic *enic)
+{
+	struct vnic_rq *rq = &enic->admin_rq;
+	u32 running;
+	int err;
+	int i;
 
-	enic_admin_qp_type_set(enic, QP_DISABLE);
+	/* Preserve the two disable/check passes used for the RQ mini-cache. */
+	for (i = 0; i < 2; i++) {
+		iowrite32(0, &rq->ctrl->enable);
+		err = read_poll_timeout(ioread32, running, !running, 10, 500000,
+					false, &rq->ctrl->running);
+		if (err)
+			return err;
+	}
 
-	err = vnic_wq_disable(&enic->admin_wq);
-	if (err)
-		netdev_warn(enic->netdev,
-			    "Failed to disable admin WQ: %d\n", err);
-	err = vnic_rq_disable(&enic->admin_rq);
-	if (err)
-		netdev_warn(enic->netdev,
-			    "Failed to disable admin RQ: %d\n", err);
+	return 0;
+}
 
+static void enic_admin_channel_release(struct enic *enic)
+{
 	vnic_wq_clean(&enic->admin_wq, enic_admin_wq_buf_clean);
 	enic_admin_rq_drain(enic);
 	vnic_cq_clean(&enic->admin_cq[0]);

@@ -662,6 +661,111 @@ void enic_admin_channel_close(struct enic *enic)
 
 	enic->admin_rq_handler = NULL;
 	enic_admin_free_resources(enic);
+	WRITE_ONCE(enic->admin_chan_state, ENIC_ADMIN_CHAN_DOWN);
+}
+
+int enic_admin_channel_close(struct enic *enic)
+{
+	int qp_err;
+	int rq_err;
+	int wq_err;
 
-	enic->admin_chan_up = false;
+	if (!enic->has_admin_channel)
+		return 0;
+	if (READ_ONCE(enic->admin_chan_state) == ENIC_ADMIN_CHAN_DOWN)
+		return 0;
+	if (READ_ONCE(enic->admin_chan_state) == ENIC_ADMIN_CHAN_QUARANTINED)
+		return -EBUSY;
+
+	WRITE_ONCE(enic->mbox_send_disabled, true);
+
+	if (READ_ONCE(enic->admin_chan_state) == ENIC_ADMIN_CHAN_LIVE) {
+		netdev_dbg(enic->netdev, "admin channel quiesce\n");
+
+		vnic_intr_mask(&enic->admin_intr);
+		enic_admin_teardown_intr(enic);
+		cancel_work_sync(&enic->link_notify_work);
+		cancel_work_sync(&enic->admin_msg_work);
+		enic_admin_msg_drain(enic);
+	}
+
+	/* A sender may have passed the gate before it was raised.  Wait only
+	 * after cancelling workers which can themselves wait for mbox_lock.
+	 */
+	mutex_lock(&enic->mbox_lock);
+	qp_err = enic_admin_qp_type_set(enic, QP_DISABLE);
+	if (qp_err)
+		netdev_warn(enic->netdev,
+			    "Failed to disable admin QP type: %d\n", qp_err);
+
+	wq_err = enic_admin_wq_disable(enic);
+	rq_err = enic_admin_rq_disable(enic);
+
+	/* Run both complete disable helpers once before retrying only a helper
+	 * which timed out.
+	 */
+	if (wq_err == -ETIMEDOUT)
+		wq_err = enic_admin_wq_disable(enic);
+	if (rq_err == -ETIMEDOUT)
+		rq_err = enic_admin_rq_disable(enic);
+
+	if (wq_err)
+		netdev_warn(enic->netdev,
+			    "Failed to disable admin WQ after retry: %d\n",
+			    wq_err);
+	if (rq_err)
+		netdev_warn(enic->netdev,
+			    "Failed to disable admin RQ after retry: %d\n",
+			    rq_err);
+
+	/* QP_DISABLE does not report every low-level stop failure.  The direct
+	 * WQ/RQ RUNNING observations own the admin allocation graph.
+	 */
+	if (wq_err || rq_err) {
+		WRITE_ONCE(enic->admin_chan_state, ENIC_ADMIN_CHAN_QUARANTINED);
+		mutex_unlock(&enic->mbox_lock);
+		/* Retained targets remain valid for late DMA. Keep bus mastering
+		 * enabled for the independent datapath and command transport.
+		 */
+		return wq_err ?: rq_err;
+	}
+
+	enic_admin_channel_release(enic);
+	mutex_unlock(&enic->mbox_lock);
+
+	/* Firmware rejection does not undermine the WQ/RQ proof. */
+	return qp_err;
+}
+
+int enic_admin_channel_final_recheck(struct enic *enic)
+{
+	int rq_err;
+	int wq_err;
+
+	if (READ_ONCE(enic->admin_chan_state) != ENIC_ADMIN_CHAN_QUARANTINED)
+		return 0;
+
+	/* Channel close already detached every CPU entry point and attempted
+	 * QP_DISABLE. This is the final direct check of queue ownership.
+	 */
+	mutex_lock(&enic->mbox_lock);
+	wq_err = enic_admin_wq_disable(enic);
+	rq_err = enic_admin_rq_disable(enic);
+	if (wq_err || rq_err) {
+		mutex_unlock(&enic->mbox_lock);
+		return wq_err ?: rq_err;
+	}
+
+	enic_admin_channel_release(enic);
+	mutex_unlock(&enic->mbox_lock);
+	netdev_info(enic->netdev,
+		    "Admin queues stopped during final teardown; releasing DMA graph\n");
+
+	return 0;
+}
+
+bool enic_admin_channel_is_quarantined(const struct enic *enic)
+{
+	return READ_ONCE(enic->admin_chan_state) ==
+		ENIC_ADMIN_CHAN_QUARANTINED;
 }

@@ -20,7 +20,9 @@ struct enic_admin_msg {
 };
 
 int enic_admin_channel_open(struct enic *enic);
-void enic_admin_channel_close(struct enic *enic);
+int enic_admin_channel_close(struct enic *enic);
+int enic_admin_channel_final_recheck(struct enic *enic);
+bool enic_admin_channel_is_quarantined(const struct enic *enic);
 unsigned int enic_admin_wq_cq_service(struct enic *enic);
 unsigned int enic_admin_rq_cq_service(struct enic *enic);
 

@@ -1736,6 +1736,13 @@ static int enic_open(struct net_device *netdev)
 		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
 	};
 
+	/* Internal reopen paths also bypass the networking core's presence check. */
+	if (!netif_device_present(netdev))
+		return -ENODEV;
+	if (enic_is_sriov_vf_v2(enic) &&
+	    enic_admin_channel_is_quarantined(enic))
+		return -EBUSY;
+
 	err = enic_request_intr(enic);
 	if (err) {
 		netdev_err(netdev, "Unable to request irq.\n");

@@ -2206,6 +2213,9 @@ static void enic_admin_chan_reopen(struct enic *enic)
 {
 	int err;
 
+	if (enic_admin_channel_is_quarantined(enic))
+		return;
+
 	/* Install the MBOX receive handler and clear pending reply state before
 	 * opening the channel, so the handler is in place before the admin
 	 * interrupt is unmasked and no early completion is dropped.  Keep the

@@ -2237,6 +2247,7 @@ static void enic_admin_chan_reopen(struct enic *enic)
 				   "MBOX capability check after reset failed: %d\n",
 				   err);
 			enic_admin_channel_close(enic);
+			WRITE_ONCE(enic->vf_registered, false);
 			return;
 		}
 		err = enic_mbox_vf_register(enic);

@@ -2245,6 +2256,7 @@ static void enic_admin_chan_reopen(struct enic *enic)
 				   "MBOX VF re-registration after reset failed: %d\n",
 				   err);
 			enic_admin_channel_close(enic);
+			WRITE_ONCE(enic->vf_registered, false);
 		}
 	} else {
 		/* The link came back up during enic_open() above while MBOX

@@ -2264,17 +2276,27 @@ static void enic_reset(struct work_struct *work)
 
 	rtnl_lock();
 
+	if (!netif_running(enic->netdev))
+		goto unlock;
+
 	/* Stop any activity from infiniband */
 	enic_set_api_busy(enic, true);
 
-	/* Fully tear down the V2 admin/MBOX channel before the soft reset.
-	 * The reset wipes all hardware queues including the admin WQ/RQ;
-	 * closing first tells firmware to stop the admin QP (so it no longer
-	 * DMAs from the about-to-be-reset rings) and frees the admin resources
-	 * so they are cleanly re-allocated afterwards.
+	/* Close the V2 admin/MBOX channel before the soft reset. Release its
+	 * DMA resources only after both queues report stopped; otherwise
+	 * quarantine the channel and abandon the reset.
 	 */
-	if (enic_has_admin_chan(enic))
+	if (enic_has_admin_chan(enic)) {
 		enic_admin_channel_close(enic);
+		/* Channel close has drained registration replies. */
+		if (enic_is_sriov_vf_v2(enic))
+			WRITE_ONCE(enic->vf_registered, false);
+	}
+	if (enic_admin_channel_is_quarantined(enic)) {
+		/* Core close excludes netpoll and clears __LINK_STATE_START first. */
+		dev_close(enic->netdev);
+		goto reset_out;
+	}
 
 	enic_stop(enic->netdev);
 	if (enic_is_sriov_vf_v2(enic))

@@ -2287,7 +2309,8 @@ static void enic_reset(struct work_struct *work)
 	enic_dev_set_ig_vlan_rewrite_mode(enic);
 	enic_ext_cq(enic);
 
-	enic_open(enic->netdev);
+	if (enic_open(enic->netdev))
+		goto reset_out;
 
 	/* Re-establish the admin/MBOX channel after the data path is back up.
 	 * It was fully torn down by enic_admin_channel_close() above;

@@ -2296,12 +2319,17 @@ static void enic_reset(struct work_struct *work)
 	 */
 	if (enic_has_admin_chan(enic))
 		enic_admin_chan_reopen(enic);
+	if (enic_is_sriov_vf_v2(enic) &&
+	    enic_admin_channel_is_quarantined(enic))
+		dev_close(enic->netdev);
 
+reset_out:
 	/* Allow infiniband to fiddle with the device again */
 	enic_set_api_busy(enic, false);
 
 	call_netdevice_notifiers(NETDEV_REBOOT, enic->netdev);
 
+unlock:
 	rtnl_unlock();
 }
 

@@ -2311,15 +2339,26 @@ static void enic_tx_hang_reset(struct work_struct *work)
 
 	rtnl_lock();
 
+	if (!netif_running(enic->netdev))
+		goto unlock;
+
 	/* Stop any activity from infiniband */
 	enic_set_api_busy(enic, true);
 
-	/* Fully tear down the V2 admin/MBOX channel before the hang reset, for
-	 * the same reason as the soft reset path: stop the admin QP and free
-	 * the admin resources before the hardware queues are wiped.
+	/* Close the V2 admin/MBOX channel before the hang reset. Release its
+	 * DMA resources only after both queues report stopped; otherwise
+	 * quarantine the channel and abandon the reset.
 	 */
-	if (enic_has_admin_chan(enic))
+	if (enic_has_admin_chan(enic)) {
 		enic_admin_channel_close(enic);
+		/* Channel close has drained registration replies. */
+		if (enic_is_sriov_vf_v2(enic))
+			WRITE_ONCE(enic->vf_registered, false);
+	}
+	if (enic_admin_channel_is_quarantined(enic)) {
+		dev_close(enic->netdev);
+		goto reset_out;
+	}
 
 	enic_dev_hang_notify(enic);
 	enic_stop(enic->netdev);

@@ -2333,7 +2372,8 @@ static void enic_tx_hang_reset(struct work_struct *work)
 	enic_dev_set_ig_vlan_rewrite_mode(enic);
 	enic_ext_cq(enic);
 
-	enic_open(enic->netdev);
+	if (enic_open(enic->netdev))
+		goto reset_out;
 
 	/* Re-establish the admin/MBOX channel after the data path is back up.
 	 * It was fully torn down by enic_admin_channel_close() above;

@@ -2342,12 +2382,17 @@ static void enic_tx_hang_reset(struct work_struct *work)
 	 */
 	if (enic_has_admin_chan(enic))
 		enic_admin_chan_reopen(enic);
+	if (enic_is_sriov_vf_v2(enic) &&
+	    enic_admin_channel_is_quarantined(enic))
+		dev_close(enic->netdev);
 
+reset_out:
 	/* Allow infiniband to fiddle with the device again */
 	enic_set_api_busy(enic, false);
 
 	call_netdevice_notifiers(NETDEV_REBOOT, enic->netdev);
 
+unlock:
 	rtnl_unlock();
 }
 

@@ -3036,7 +3081,8 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_free_netdev;
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
+	/* A terminal admin allocation keeps the reservation after module unload. */
+	err = pci_request_regions(pdev, dev_name(dev));
 	if (err) {
 		dev_err(dev, "Cannot request PCI regions, aborting\n");
 		goto err_out_disable_device;

@@ -3364,6 +3410,8 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	enic_dev_deinit(enic);
 err_out_dev_close:
 	vnic_dev_close(enic->vdev);
+	if (enic_admin_channel_is_quarantined(enic))
+		enic_admin_channel_final_recheck(enic);
 err_out_disable_sriov:
 	kfree(enic->pp);
 err_out_disable_sriov_pp:

@@ -3374,6 +3422,17 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 #endif
 err_out_vnic_unregister:
+	if (enic_admin_channel_is_quarantined(enic)) {
+		/* Normal generic cleanup and CMD_CLOSE have already run. Retain
+		 * only the inert admin/control owners and their PCI reservation.
+		 */
+		pci_dev_get(pdev);
+		pci_clear_master(pdev);
+		pci_disable_device(pdev);
+		pci_set_drvdata(pdev, NULL);
+		dev_err(dev, "Control DMA unresolved; retaining resources until reboot\n");
+		return err;
+	}
 	vnic_dev_unregister(enic->vdev);
 err_out_iounmap:
 	enic_iounmap(enic);

@@ -3397,6 +3456,9 @@ static void enic_remove(struct pci_dev *pdev)
 		disable_work_sync(&enic->reset);
 		disable_work_sync(&enic->tx_hang_reset);
 		disable_work_sync(&enic->change_mtu_work);
+		rtnl_lock();
+		netif_device_detach(netdev);
+		rtnl_unlock();
 
 		/* Close the admin channel and unregister from the PF before
 		 * unregister_netdev() to prevent a late PF notification from

@@ -3431,7 +3493,23 @@ static void enic_remove(struct pci_dev *pdev)
 #endif
 		enic_dev_deinit(enic);
 		vnic_dev_close(enic->vdev);
+		if (enic_admin_channel_is_quarantined(enic))
+			enic_admin_channel_final_recheck(enic);
 		kfree(enic->pp);
+		if (enic_admin_channel_is_quarantined(enic)) {
+			/* All generic queues and CPU entry points followed ordinary
+			 * teardown. No admin buffer can return from the network stack.
+			 * Pin the PCI object for the reservation's owner-name pointer;
+			 * this reference does not fence DMA or preserve IOMMU state.
+			 */
+			pci_dev_get(pdev);
+			pci_clear_master(pdev);
+			pci_disable_device(pdev);
+			pci_set_drvdata(pdev, NULL);
+			dev_err(&pdev->dev,
+				"Control DMA unresolved; retaining resources until reboot\n");
+			return;
+		}
 		vnic_dev_unregister(enic->vdev);
 		enic_iounmap(enic);
 		pci_release_regions(pdev);