RDMA 5.11 second RC pull request

Several recent regressions and some bug fixes
 
 - Typo corrupting the max_recv_sge for cxgb4
 
 - Regression from re-using kernel enums as a HW AbI in vmw_pvrdma
 
 - Sleeping inside a spinlock in hns
 
 - Revert the attempt to fix devlink deadlocks as the fix is more buggy
 
 - Typo in sysfs_emit_at conversions
 
 - Revert the removal of VLAN support in rxe
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEfB7FMLh+8QxL+6i3OG33FX4gmxoFAmASxQwACgkQOG33FX4g
 mxq5uw/6AwjSrC2gP46uZTB+aWN7EeFqk4+/OkxBWOrvp9TNRrrwu7dYum988It4
 FJCighjyk0lcF75Ma/5Q7D2+V6DextMoSxaLb1RLHCGi50VhzzaSI2NtGjFxaZ1G
 GILNusIFraR9dqx+T2TK+AN5hCnek+yYIsrr6AOh0Vd29NFy4U8XDxkjnisiNO+z
 vKAiAbk5cHHi8DLU6TwdTUtg+jozlqUP4g79nQ3WjqLywPbcLFHNj0VdaaEBHaqC
 m1VR4hDdPpkzvdLJv46tgy79y2BjEt04Q/pHGTLL+qvZGHefcIw7aRC2Mg6+6ytI
 lVhjYkBR5UrE7/H6BEYvqVcneOypWXZFdF8Jxl4dzkZPQZ5wh0J2LZykQD3LCn8K
 OHcy4ZZlgBnWtwAO8zK60kmZ0otl1Yc2sz7hOniLUYPrVsZoPWA+Zqqv15KFHAT+
 +pbv4O6A9tmDshIw/XSensbb9XQy6ngAxWqkV7/zNfVbf52vyDblkOfuYJB7cFfp
 mEEoC4oBP1IyKrcOzlWa6v30oOlIqT0CmJTmhnFhiMI4x6j67cqJRccjxYA2kuU3
 uHhSHYNcZjwuOr1D0qat9GfxWBKV8SziwGj4S7tgYxVnBTE6o/f1b+0Aq+dmkXtM
 QUATE/HgfMBZZUBwdVQz3so9UbQqQGKrVFo3viI5O+CbRqArosY=
 =P74g
 -----END PGP SIGNATURE-----

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma fixes from Jason Gunthorpe:
 "Several recent regressions and some bug fixes:

   - Typo corrupting the max_recv_sge for cxgb4

   - Regression from re-using kernel enums as a HW AbI in vmw_pvrdma

   - Sleeping inside a spinlock in hns

   - Revert the attempt to fix devlink deadlocks as the fix is more buggy

   - Typo in sysfs_emit_at conversions

   - Revert the removal of VLAN support in rxe"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  Revert "RDMA/rxe: Remove VLAN code leftovers from RXE"
  RDMA/usnic: Fix misuse of sysfs_emit_at
  Revert "RDMA/mlx5: Fix devlink deadlock on net namespace deletion"
  RDMA/hns: Use mutex instead of spinlock for ida allocation
  RDMA/vmw_pvrdma: Fix network_hdr_type reported in WC
  RDMA/cxgb4: Fix the reported max_recv_sge value

drivers/infiniband/hw/cxgb4/qp.c

@@ -2474,7 +2474,7 @@ int c4iw_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	init_attr->cap.max_send_wr = qhp->attr.sq_num_entries;
 	init_attr->cap.max_recv_wr = qhp->attr.rq_num_entries;
 	init_attr->cap.max_send_sge = qhp->attr.sq_max_sges;
-	init_attr->cap.max_recv_sge = qhp->attr.sq_max_sges;
+	init_attr->cap.max_recv_sge = qhp->attr.rq_max_sges;
 	init_attr->cap.max_inline_data = T4_MAX_SEND_INLINE;
 	init_attr->sq_sig_type = qhp->sq_sig_all ? IB_SIGNAL_ALL_WR : 0;
 	return 0;

drivers/infiniband/hw/hns/hns_roce_device.h

@@ -532,7 +532,7 @@ struct hns_roce_qp_table {
 	struct hns_roce_hem_table	sccc_table;
 	struct mutex			scc_mutex;
 	struct hns_roce_bank bank[HNS_ROCE_QP_BANK_NUM];
-	spinlock_t bank_lock;
+	struct mutex bank_mutex;
 };
 
 struct hns_roce_cq_table {

drivers/infiniband/hw/hns/hns_roce_qp.c

@@ -209,7 +209,7 @@ static int alloc_qpn(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp)
 
 		hr_qp->doorbell_qpn = 1;
 	} else {
-		spin_lock(&qp_table->bank_lock);
+		mutex_lock(&qp_table->bank_mutex);
 		bankid = get_least_load_bankid_for_qp(qp_table->bank);
 
 		ret = alloc_qpn_with_bankid(&qp_table->bank[bankid], bankid,
@@ -217,12 +217,12 @@ static int alloc_qpn(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp)
 		if (ret) {
 			ibdev_err(&hr_dev->ib_dev,
 				  "failed to alloc QPN, ret = %d\n", ret);
-			spin_unlock(&qp_table->bank_lock);
+			mutex_unlock(&qp_table->bank_mutex);
 			return ret;
 		}
 
 		qp_table->bank[bankid].inuse++;
-		spin_unlock(&qp_table->bank_lock);
+		mutex_unlock(&qp_table->bank_mutex);
 
 		hr_qp->doorbell_qpn = (u32)num;
 	}
@@ -408,9 +408,9 @@ static void free_qpn(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp)
 
 	ida_free(&hr_dev->qp_table.bank[bankid].ida, hr_qp->qpn >> 3);
 
-	spin_lock(&hr_dev->qp_table.bank_lock);
+	mutex_lock(&hr_dev->qp_table.bank_mutex);
 	hr_dev->qp_table.bank[bankid].inuse--;
-	spin_unlock(&hr_dev->qp_table.bank_lock);
+	mutex_unlock(&hr_dev->qp_table.bank_mutex);
 }
 
 static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap,
@@ -1371,6 +1371,7 @@ int hns_roce_init_qp_table(struct hns_roce_dev *hr_dev)
 	unsigned int i;
 
 	mutex_init(&qp_table->scc_mutex);
+	mutex_init(&qp_table->bank_mutex);
 	xa_init(&hr_dev->qp_table_xa);
 
 	reserved_from_bot = hr_dev->caps.reserved_qps;

drivers/infiniband/hw/mlx5/main.c

@@ -3311,8 +3311,7 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 	int err;
 
 	dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event;
-	err = register_netdevice_notifier_net(mlx5_core_net(dev->mdev),
-					      &dev->port[port_num].roce.nb);
+	err = register_netdevice_notifier(&dev->port[port_num].roce.nb);
 	if (err) {
 		dev->port[port_num].roce.nb.notifier_call = NULL;
 		return err;
@@ -3324,8 +3323,7 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 {
 	if (dev->port[port_num].roce.nb.notifier_call) {
-		unregister_netdevice_notifier_net(mlx5_core_net(dev->mdev),
-						  &dev->port[port_num].roce.nb);
+		unregister_netdevice_notifier(&dev->port[port_num].roce.nb);
 		dev->port[port_num].roce.nb.notifier_call = NULL;
 	}
 }

drivers/infiniband/hw/usnic/usnic_ib_sysfs.c

@@ -214,7 +214,7 @@ static ssize_t summary_show(struct usnic_ib_qp_grp *qp_grp, char *buf)
 	struct usnic_vnic_res *vnic_res;
 	int len;
 
-	len = sysfs_emit(buf, "QPN: %d State: (%s) PID: %u VF Idx: %hu ",
+	len = sysfs_emit(buf, "QPN: %d State: (%s) PID: %u VF Idx: %hu",
 			 qp_grp->ibqp.qp_num,
 			 usnic_ib_qp_grp_state_to_string(qp_grp->state),
 			 qp_grp->owner_pid,
@@ -224,14 +224,13 @@ static ssize_t summary_show(struct usnic_ib_qp_grp *qp_grp, char *buf)
 		res_chunk = qp_grp->res_chunk_list[i];
 		for (j = 0; j < res_chunk->cnt; j++) {
 			vnic_res = res_chunk->res[j];
-			len += sysfs_emit_at(
-				buf, len, "%s[%d] ",
+			len += sysfs_emit_at(buf, len, " %s[%d]",
 				usnic_vnic_res_type_to_str(vnic_res->type),
 				vnic_res->vnic_idx);
 		}
 	}
 
-	len = sysfs_emit_at(buf, len, "\n");
+	len += sysfs_emit_at(buf, len, "\n");
 
 	return len;
 }

drivers/infiniband/hw/vmw_pvrdma/pvrdma.h

@@ -509,6 +509,20 @@ static inline int ib_send_flags_to_pvrdma(int flags)
 	return flags & PVRDMA_MASK(PVRDMA_SEND_FLAGS_MAX);
 }
 
+static inline int pvrdma_network_type_to_ib(enum pvrdma_network_type type)
+{
+	switch (type) {
+	case PVRDMA_NETWORK_ROCE_V1:
+		return RDMA_NETWORK_ROCE_V1;
+	case PVRDMA_NETWORK_IPV4:
+		return RDMA_NETWORK_IPV4;
+	case PVRDMA_NETWORK_IPV6:
+		return RDMA_NETWORK_IPV6;
+	default:
+		return RDMA_NETWORK_IPV6;
+	}
+}
+
 void pvrdma_qp_cap_to_ib(struct ib_qp_cap *dst,
 			 const struct pvrdma_qp_cap *src);
 void ib_qp_cap_to_pvrdma(struct pvrdma_qp_cap *dst,

drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c

@@ -367,7 +367,7 @@ static int pvrdma_poll_one(struct pvrdma_cq *cq, struct pvrdma_qp **cur_qp,
 	wc->dlid_path_bits = cqe->dlid_path_bits;
 	wc->port_num = cqe->port_num;
 	wc->vendor_err = cqe->vendor_err;
-	wc->network_hdr_type = cqe->network_hdr_type;
+	wc->network_hdr_type = pvrdma_network_type_to_ib(cqe->network_hdr_type);
 
 	/* Update shared ring state */
 	pvrdma_idx_ring_inc(&cq->ring_state->rx.cons_head, cq->ibcq.cqe);

drivers/infiniband/sw/rxe/rxe_net.c

@@ -8,6 +8,7 @@
 #include <linux/if_arp.h>
 #include <linux/netdevice.h>
 #include <linux/if.h>
+#include <linux/if_vlan.h>
 #include <net/udp_tunnel.h>
 #include <net/sch_generic.h>
 #include <linux/netfilter.h>
@@ -153,9 +154,14 @@ static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct udphdr *udph;
 	struct net_device *ndev = skb->dev;
+	struct net_device *rdev = ndev;
 	struct rxe_dev *rxe = rxe_get_dev_from_net(ndev);
 	struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
 
+	if (!rxe && is_vlan_dev(rdev)) {
+		rdev = vlan_dev_real_dev(ndev);
+		rxe = rxe_get_dev_from_net(rdev);
+	}
 	if (!rxe)
 		goto drop;
 

drivers/infiniband/sw/rxe/rxe_resp.c

@@ -872,6 +872,11 @@ static enum resp_states do_complete(struct rxe_qp *qp,
 			else
 				wc->network_hdr_type = RDMA_NETWORK_IPV6;
 
+			if (is_vlan_dev(skb->dev)) {
+				wc->wc_flags |= IB_WC_WITH_VLAN;
+				wc->vlan_id = vlan_dev_vlan_id(skb->dev);
+			}
+
 			if (pkt->mask & RXE_IMMDT_MASK) {
 				wc->wc_flags |= IB_WC_WITH_IMM;
 				wc->ex.imm_data = immdt_imm(pkt);

drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h

@@ -90,4 +90,9 @@ int mlx5_create_encryption_key(struct mlx5_core_dev *mdev,
 			       u32 key_type, u32 *p_key_id);
 void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id);
 
+static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
+{
+	return devlink_net(priv_to_devlink(dev));
+}
+
 #endif

include/linux/mlx5/driver.h

@@ -1209,22 +1209,4 @@ static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev)
 	return val.vbool;
 }
 
-/**
- * mlx5_core_net - Provide net namespace of the mlx5_core_dev
- * @dev: mlx5 core device
- *
- * mlx5_core_net() returns the net namespace of mlx5 core device.
- * This can be called only in below described limited context.
- * (a) When a devlink instance for mlx5_core is registered and
- *     when devlink reload operation is disabled.
- *     or
- * (b) during devlink reload reload_down() and reload_up callbacks
- *     where it is ensured that devlink instance's net namespace is
- *     stable.
- */
-static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
-{
-	return devlink_net(priv_to_devlink(dev));
-}
-
 #endif /* MLX5_DRIVER_H */

include/uapi/rdma/vmw_pvrdma-abi.h

@@ -133,6 +133,13 @@ enum pvrdma_wc_flags {
 	PVRDMA_WC_FLAGS_MAX		= PVRDMA_WC_WITH_NETWORK_HDR_TYPE,
 };
 
+enum pvrdma_network_type {
+	PVRDMA_NETWORK_IB,
+	PVRDMA_NETWORK_ROCE_V1 = PVRDMA_NETWORK_IB,
+	PVRDMA_NETWORK_IPV4,
+	PVRDMA_NETWORK_IPV6
+};
+
 struct pvrdma_alloc_ucontext_resp {
 	__u32 qp_tab_size;
 	__u32 reserved;