Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue

Tony Nguyen says:

====================
ice: fix synchronization between .ndo_bpf() and reset

Larysa Zaremba says:

PF reset can be triggered asynchronously, by tx_timeout or by a user. With some
unfortunate timings both ice_vsi_rebuild() and .ndo_bpf will try to access and
modify XDP rings at the same time, causing system crash.

The first patch factors out rtnl-locked code from VSI rebuild code to avoid
deadlock. The following changes lock rebuild and .ndo_bpf() critical sections
with an internal mutex as well and provide complementary fixes.

* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue:
  ice: do not bring the VSI up, if it was down before the XDP setup
  ice: remove ICE_CFG_BUSY locking from AF_XDP code
  ice: check ICE_VSI_DOWN under rtnl_lock when preparing for reset
  ice: check for XDP rings instead of bpf program when unconfiguring
  ice: protect XDP configuration with a mutex
  ice: move netif_queue_set_napi to rtnl-protected sections
====================

Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

drivers/net/ethernet/intel/ice/ice.h

@@ -318,6 +318,7 @@ enum ice_vsi_state {
 	ICE_VSI_UMAC_FLTR_CHANGED,
 	ICE_VSI_MMAC_FLTR_CHANGED,
 	ICE_VSI_PROMISC_CHANGED,
+	ICE_VSI_REBUILD_PENDING,
 	ICE_VSI_STATE_NBITS		/* must be last */
 };
 
@@ -411,6 +412,7 @@ struct ice_vsi {
 	struct ice_tx_ring **xdp_rings;	 /* XDP ring array */
 	u16 num_xdp_txq;		 /* Used XDP queues */
 	u8 xdp_mapping_mode;		 /* ICE_MAP_MODE_[CONTIG|SCATTER] */
+	struct mutex xdp_state_lock;
 
 	struct net_device **target_netdevs;
 

drivers/net/ethernet/intel/ice/ice_base.c

@@ -190,16 +190,11 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
 	}
 	q_vector = vsi->q_vectors[v_idx];
 
-	ice_for_each_tx_ring(tx_ring, q_vector->tx) {
-		ice_queue_set_napi(vsi, tx_ring->q_index, NETDEV_QUEUE_TYPE_TX,
-				   NULL);
+	ice_for_each_tx_ring(tx_ring, vsi->q_vectors[v_idx]->tx)
 		tx_ring->q_vector = NULL;
-	}
-	ice_for_each_rx_ring(rx_ring, q_vector->rx) {
-		ice_queue_set_napi(vsi, rx_ring->q_index, NETDEV_QUEUE_TYPE_RX,
-				   NULL);
+
+	ice_for_each_rx_ring(rx_ring, vsi->q_vectors[v_idx]->rx)
 		rx_ring->q_vector = NULL;
-	}
 
 	/* only VSI with an associated netdev is set up with NAPI */
 	if (vsi->netdev)

drivers/net/ethernet/intel/ice/ice_lib.c

@@ -447,6 +447,7 @@ static void ice_vsi_free(struct ice_vsi *vsi)
 
 	ice_vsi_free_stats(vsi);
 	ice_vsi_free_arrays(vsi);
+	mutex_destroy(&vsi->xdp_state_lock);
 	mutex_unlock(&pf->sw_mutex);
 	devm_kfree(dev, vsi);
 }
@@ -626,6 +627,8 @@ static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf)
 	pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi,
 					 pf->next_vsi);
 
+	mutex_init(&vsi->xdp_state_lock);
+
 unlock_pf:
 	mutex_unlock(&pf->sw_mutex);
 	return vsi;
@@ -2286,9 +2289,6 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
 
 		ice_vsi_map_rings_to_vectors(vsi);
 
-		/* Associate q_vector rings to napi */
-		ice_vsi_set_napi_queues(vsi);
-
 		vsi->stat_offsets_loaded = false;
 
 		/* ICE_VSI_CTRL does not need RSS so skip RSS processing */
@@ -2426,7 +2426,7 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
 		dev_err(ice_pf_to_dev(pf), "Failed to remove RDMA scheduler config for VSI %u, err %d\n",
 			vsi->vsi_num, err);
 
-	if (ice_is_xdp_ena_vsi(vsi))
+	if (vsi->xdp_rings)
 		/* return value check can be skipped here, it always returns
 		 * 0 if reset is in progress
 		 */
@@ -2528,7 +2528,7 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi)
 		for (q = 0; q < q_vector->num_ring_tx; q++) {
 			ice_write_itr(&q_vector->tx, 0);
 			wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0);
-			if (ice_is_xdp_ena_vsi(vsi)) {
+			if (vsi->xdp_rings) {
 				u32 xdp_txq = txq + vsi->num_xdp_txq;
 
 				wr32(hw, QINT_TQCTL(vsi->txq_map[xdp_txq]), 0);
@@ -2628,6 +2628,7 @@ void ice_vsi_close(struct ice_vsi *vsi)
 	if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state))
 		ice_down(vsi);
 
+	ice_vsi_clear_napi_queues(vsi);
 	ice_vsi_free_irq(vsi);
 	ice_vsi_free_tx_rings(vsi);
 	ice_vsi_free_rx_rings(vsi);
@@ -2671,143 +2672,78 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
  */
 void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
 {
-	if (test_bit(ICE_VSI_DOWN, vsi->state))
-		return;
+	bool already_down = test_bit(ICE_VSI_DOWN, vsi->state);
 
 	set_bit(ICE_VSI_NEEDS_RESTART, vsi->state);
 
 	if (vsi->type == ICE_VSI_PF && vsi->netdev) {
 		if (netif_running(vsi->netdev)) {
 			if (!locked)
 				rtnl_lock();
-
-			ice_vsi_close(vsi);
+			already_down = test_bit(ICE_VSI_DOWN, vsi->state);
+			if (!already_down)
+				ice_vsi_close(vsi);
 
 			if (!locked)
 				rtnl_unlock();
-		} else {
+		} else if (!already_down) {
 			ice_vsi_close(vsi);
 		}
-	} else if (vsi->type == ICE_VSI_CTRL) {
+	} else if (vsi->type == ICE_VSI_CTRL && !already_down) {
 		ice_vsi_close(vsi);
 	}
 }
 
 /**
- * __ice_queue_set_napi - Set the napi instance for the queue
- * @dev: device to which NAPI and queue belong
- * @queue_index: Index of queue
- * @type: queue type as RX or TX
- * @napi: NAPI context
- * @locked: is the rtnl_lock already held
- *
- * Set the napi instance for the queue. Caller indicates the lock status.
- */
-static void
-__ice_queue_set_napi(struct net_device *dev, unsigned int queue_index,
-		     enum netdev_queue_type type, struct napi_struct *napi,
-		     bool locked)
-{
-	if (!locked)
-		rtnl_lock();
-	netif_queue_set_napi(dev, queue_index, type, napi);
-	if (!locked)
-		rtnl_unlock();
-}
-
-/**
- * ice_queue_set_napi - Set the napi instance for the queue
- * @vsi: VSI being configured
- * @queue_index: Index of queue
- * @type: queue type as RX or TX
- * @napi: NAPI context
+ * ice_vsi_set_napi_queues - associate netdev queues with napi
+ * @vsi: VSI pointer
  *
- * Set the napi instance for the queue. The rtnl lock state is derived from the
- * execution path.
+ * Associate queue[s] with napi for all vectors.
+ * The caller must hold rtnl_lock.
  */
-void
-ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
-		   enum netdev_queue_type type, struct napi_struct *napi)
+void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
 {
-	struct ice_pf *pf = vsi->back;
+	struct net_device *netdev = vsi->netdev;
+	int q_idx, v_idx;
 
-	if (!vsi->netdev)
+	if (!netdev)
 		return;
 
-	if (current_work() == &pf->serv_task ||
-	    test_bit(ICE_PREPARED_FOR_RESET, pf->state) ||
-	    test_bit(ICE_DOWN, pf->state) ||
-	    test_bit(ICE_SUSPENDED, pf->state))
-		__ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
-				     false);
-	else
-		__ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
-				     true);
-}
+	ice_for_each_rxq(vsi, q_idx)
+		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX,
+				     &vsi->rx_rings[q_idx]->q_vector->napi);
 
-/**
- * __ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
- * @q_vector: q_vector pointer
- * @locked: is the rtnl_lock already held
- *
- * Associate the q_vector napi with all the queue[s] on the vector.
- * Caller indicates the lock status.
- */
-void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
-{
-	struct ice_rx_ring *rx_ring;
-	struct ice_tx_ring *tx_ring;
-
-	ice_for_each_rx_ring(rx_ring, q_vector->rx)
-		__ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index,
-				     NETDEV_QUEUE_TYPE_RX, &q_vector->napi,
-				     locked);
-
-	ice_for_each_tx_ring(tx_ring, q_vector->tx)
-		__ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index,
-				     NETDEV_QUEUE_TYPE_TX, &q_vector->napi,
-				     locked);
+	ice_for_each_txq(vsi, q_idx)
+		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX,
+				     &vsi->tx_rings[q_idx]->q_vector->napi);
 	/* Also set the interrupt number for the NAPI */
-	netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
-}
-
-/**
- * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
- * @q_vector: q_vector pointer
- *
- * Associate the q_vector napi with all the queue[s] on the vector
- */
-void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector)
-{
-	struct ice_rx_ring *rx_ring;
-	struct ice_tx_ring *tx_ring;
-
-	ice_for_each_rx_ring(rx_ring, q_vector->rx)
-		ice_queue_set_napi(q_vector->vsi, rx_ring->q_index,
-				   NETDEV_QUEUE_TYPE_RX, &q_vector->napi);
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
 
-	ice_for_each_tx_ring(tx_ring, q_vector->tx)
-		ice_queue_set_napi(q_vector->vsi, tx_ring->q_index,
-				   NETDEV_QUEUE_TYPE_TX, &q_vector->napi);
-	/* Also set the interrupt number for the NAPI */
-	netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
+		netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
+	}
 }
 
 /**
- * ice_vsi_set_napi_queues
+ * ice_vsi_clear_napi_queues - dissociate netdev queues from napi
  * @vsi: VSI pointer
  *
- * Associate queue[s] with napi for all vectors
+ * Clear the association between all VSI queues queue[s] and napi.
+ * The caller must hold rtnl_lock.
  */
-void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
+void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
 {
-	int i;
+	struct net_device *netdev = vsi->netdev;
+	int q_idx;
 
-	if (!vsi->netdev)
+	if (!netdev)
 		return;
 
-	ice_for_each_q_vector(vsi, i)
-		ice_q_vector_set_napi_queues(vsi->q_vectors[i]);
+	ice_for_each_txq(vsi, q_idx)
+		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL);
+
+	ice_for_each_rxq(vsi, q_idx)
+		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, NULL);
 }
 
 /**
@@ -3039,42 +2975,47 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
 	if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf))
 		return -EINVAL;
 
+	mutex_lock(&vsi->xdp_state_lock);
+
 	ret = ice_vsi_realloc_stat_arrays(vsi);
 	if (ret)
-		goto err_vsi_cfg;
+		goto unlock;
 
 	ice_vsi_decfg(vsi);
 	ret = ice_vsi_cfg_def(vsi);
 	if (ret)
-		goto err_vsi_cfg;
+		goto unlock;
 
 	coalesce = kcalloc(vsi->num_q_vectors,
 			   sizeof(struct ice_coalesce_stored), GFP_KERNEL);
-	if (!coalesce)
-		return -ENOMEM;
+	if (!coalesce) {
+		ret = -ENOMEM;
+		goto decfg;
+	}
 
 	prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce);
 
 	ret = ice_vsi_cfg_tc_lan(pf, vsi);
 	if (ret) {
 		if (vsi_flags & ICE_VSI_FLAG_INIT) {
 			ret = -EIO;
-			goto err_vsi_cfg_tc_lan;
+			goto free_coalesce;
 		}
 
-		kfree(coalesce);
-		return ice_schedule_reset(pf, ICE_RESET_PFR);
+		ret = ice_schedule_reset(pf, ICE_RESET_PFR);
+		goto free_coalesce;
 	}
 
 	ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors);
-	kfree(coalesce);
-
-	return 0;
+	clear_bit(ICE_VSI_REBUILD_PENDING, vsi->state);
 
-err_vsi_cfg_tc_lan:
-	ice_vsi_decfg(vsi);
+free_coalesce:
 	kfree(coalesce);
-err_vsi_cfg:
+decfg:
+	if (ret)
+		ice_vsi_decfg(vsi);
+unlock:
+	mutex_unlock(&vsi->xdp_state_lock);
 	return ret;
 }
 

drivers/net/ethernet/intel/ice/ice_lib.h

@@ -44,16 +44,10 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc);
 struct ice_vsi *
 ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params);
 
-void
-ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
-		   enum netdev_queue_type type, struct napi_struct *napi);
-
-void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked);
-
-void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector);
-
 void ice_vsi_set_napi_queues(struct ice_vsi *vsi);
 
+void ice_vsi_clear_napi_queues(struct ice_vsi *vsi);
+
 int ice_vsi_release(struct ice_vsi *vsi);
 
 void ice_vsi_close(struct ice_vsi *vsi);