5.1 First RC pull request

Several driver bug fixes post in the last three weeks
 
 - First part of a race condition fix in mlx4 with CATAS errors
 
 - Bad interaction with FW causing resource leaks in the mlx5 DCT flow
 
 - Bad reporting of link speed/width in new mlx5 devices
 
 - Userspace triggable OOPs in i40iw
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEfB7FMLh+8QxL+6i3OG33FX4gmxoFAlyO7B8ACgkQOG33FX4g
 mxoIPA//bfnWR/l0BdaGaOpZATqhYIvJXfGptmQD+/6SjNcv1ig0uDKh5Mfd4hf2
 0ltxsDmrbLtd4JOgI0IvqOdXNnbwWJIxnGCyIX6UyVKogzZnJIuRKz0YLnALHgxt
 KbuPURZPDSgMLZZnj/3WghOVw8cae5K2xPt8so+x51mUzVdJeR6GwDJ7Iuslddqv
 c4IwG5zzsxoIZcgSSQZt2nUpUpVCly5rvII+guOXdctOCb/3BtjYfbVbAWVsK284
 vTowvUS4OQJ/g2Jmej9ge9DY3Rw52+BW4NCzciJVz+QmY4hf85xt/E/6joQslRKl
 DdAYafvrg/XKW9z8FqCWm0PXPHtQ63MeOLHkLQi9n8NjXhyppHJR5fW69lOAtsrV
 V/yTTvLai+lA0Jv4bTDf/M9CkruFDjB1rlhzepytxvLGr5QcL5hwlSH0qCpVz+Xu
 v+ftS2hGKpi5uK4YNsye9tzP11eCLAzBUI5VkgvoOGWkUibUfkzOXLG0OzzkoUMK
 vaXGlkHus0dw/ojPQsNEVONZCsnB4V2LOF8wApcGtRqJocdxOzpbz0zZDLVCd7Nj
 JuOe44hWGzzDWrecqOepnV9sPi9UCPcZC6LWVdduF00RW38wxBMlLZTdpb8sEZje
 DB8QNgougQWg2UMfHAhDBFbV7/FsM/wHH7ZgIS7Xmyo8QdaAK2I=
 =klIw
 -----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 driver bug fixes post in the last three weeks

   - first part of a race condition fix in mlx4 with CATAS errors

   - bad interaction with FW causing resource leaks in the mlx5 DCT flow

   - bad reporting of link speed/width in new mlx5 devices

   - user triggable OOPS in i40iw"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  i40iw: Avoid panic when handling the inetdev event
  IB/mlx5: Fix mapping of link-mode to IB width and speed
  IB/mlx5: Use mlx5 core to create/destroy a DEVX DCT
  net/mlx5: Fix DCT creation bad flow
  IB/mlx4: Fix race condition between catas error reset and aliasguid flows

drivers/infiniband/hw/i40iw/i40iw_utils.c

@@ -173,7 +173,12 @@ int i40iw_inetaddr_event(struct notifier_block *notifier,
 
 		rcu_read_lock();
 		in = __in_dev_get_rcu(upper_dev);
-		local_ipaddr = ntohl(in->ifa_list->ifa_address);
+
+		if (!in->ifa_list)
+			local_ipaddr = 0;
+		else
+			local_ipaddr = ntohl(in->ifa_list->ifa_address);
+
 		rcu_read_unlock();
 	} else {
 		local_ipaddr = ntohl(ifa->ifa_address);
@@ -185,6 +190,11 @@ int i40iw_inetaddr_event(struct notifier_block *notifier,
 	case NETDEV_UP:
 		/* Fall through */
 	case NETDEV_CHANGEADDR:
+
+		/* Just skip if no need to handle ARP cache */
+		if (!local_ipaddr)
+			break;
+
 		i40iw_manage_arp_cache(iwdev,
 				       netdev->dev_addr,
 				       &local_ipaddr,

drivers/infiniband/hw/mlx4/alias_GUID.c

@@ -804,8 +804,8 @@ void mlx4_ib_destroy_alias_guid_service(struct mlx4_ib_dev *dev)
 	unsigned long flags;
 
 	for (i = 0 ; i < dev->num_ports; i++) {
-		cancel_delayed_work(&dev->sriov.alias_guid.ports_guid[i].alias_guid_work);
 		det = &sriov->alias_guid.ports_guid[i];
+		cancel_delayed_work_sync(&det->alias_guid_work);
 		spin_lock_irqsave(&sriov->alias_guid.ag_work_lock, flags);
 		while (!list_empty(&det->cb_list)) {
 			cb_ctx = list_entry(det->cb_list.next,

drivers/infiniband/hw/mlx5/devx.c

@@ -20,6 +20,7 @@
 
 enum devx_obj_flags {
 	DEVX_OBJ_FLAGS_INDIRECT_MKEY = 1 << 0,
+	DEVX_OBJ_FLAGS_DCT = 1 << 1,
 };
 
 struct devx_async_data {
@@ -39,7 +40,10 @@ struct devx_obj {
 	u32			dinlen; /* destroy inbox length */
 	u32			dinbox[MLX5_MAX_DESTROY_INBOX_SIZE_DW];
 	u32			flags;
-	struct mlx5_ib_devx_mr	devx_mr;
+	union {
+		struct mlx5_ib_devx_mr	devx_mr;
+		struct mlx5_core_dct	core_dct;
+	};
 };
 
 struct devx_umem {
@@ -347,7 +351,6 @@ static u64 devx_get_obj_id(const void *in)
 		obj_id = get_enc_obj_id(MLX5_CMD_OP_CREATE_RQ,
 					MLX5_GET(arm_rq_in, in, srq_number));
 		break;
-	case MLX5_CMD_OP_DRAIN_DCT:
 	case MLX5_CMD_OP_ARM_DCT_FOR_KEY_VIOLATION:
 		obj_id = get_enc_obj_id(MLX5_CMD_OP_CREATE_DCT,
 					MLX5_GET(drain_dct_in, in, dctn));
@@ -618,7 +621,6 @@ static bool devx_is_obj_modify_cmd(const void *in)
 	case MLX5_CMD_OP_2RST_QP:
 	case MLX5_CMD_OP_ARM_XRC_SRQ:
 	case MLX5_CMD_OP_ARM_RQ:
-	case MLX5_CMD_OP_DRAIN_DCT:
 	case MLX5_CMD_OP_ARM_DCT_FOR_KEY_VIOLATION:
 	case MLX5_CMD_OP_ARM_XRQ:
 	case MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY:
@@ -1124,7 +1126,11 @@ static int devx_obj_cleanup(struct ib_uobject *uobject,
 	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY)
 		devx_cleanup_mkey(obj);
 
-	ret = mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out, sizeof(out));
+	if (obj->flags & DEVX_OBJ_FLAGS_DCT)
+		ret = mlx5_core_destroy_dct(obj->mdev, &obj->core_dct);
+	else
+		ret = mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out,
+				    sizeof(out));
 	if (ib_is_destroy_retryable(ret, why, uobject))
 		return ret;
 
@@ -1185,9 +1191,17 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)(
 		devx_set_umem_valid(cmd_in);
 	}
 
-	err = mlx5_cmd_exec(dev->mdev, cmd_in,
+	if (opcode == MLX5_CMD_OP_CREATE_DCT) {
-			    cmd_in_len,
+		obj->flags |= DEVX_OBJ_FLAGS_DCT;
-			    cmd_out, cmd_out_len);
+		err = mlx5_core_create_dct(dev->mdev, &obj->core_dct,
+					   cmd_in, cmd_in_len,
+					   cmd_out, cmd_out_len);
+	} else {
+		err = mlx5_cmd_exec(dev->mdev, cmd_in,
+				    cmd_in_len,
+				    cmd_out, cmd_out_len);
+	}
+
 	if (err)
 		goto obj_free;
 
@@ -1214,7 +1228,11 @@ err_copy:
 	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY)
 		devx_cleanup_mkey(obj);
 obj_destroy:
-	mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out, sizeof(out));
+	if (obj->flags & DEVX_OBJ_FLAGS_DCT)
+		mlx5_core_destroy_dct(obj->mdev, &obj->core_dct);
+	else
+		mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out,
+			      sizeof(out));
 obj_free:
 	kfree(obj);
 	return err;

drivers/infiniband/hw/mlx5/main.c

@@ -415,10 +415,17 @@ static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u8 *active_speed,
 		*active_speed = IB_SPEED_EDR;
 		break;
 	case MLX5E_PROT_MASK(MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2):
+		*active_width = IB_WIDTH_2X;
+		*active_speed = IB_SPEED_EDR;
+		break;
 	case MLX5E_PROT_MASK(MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR):
 		*active_width = IB_WIDTH_1X;
 		*active_speed = IB_SPEED_HDR;
 		break;
+	case MLX5E_PROT_MASK(MLX5E_CAUI_4_100GBASE_CR4_KR4):
+		*active_width = IB_WIDTH_4X;
+		*active_speed = IB_SPEED_EDR;
+		break;
 	case MLX5E_PROT_MASK(MLX5E_100GAUI_2_100GBASE_CR2_KR2):
 		*active_width = IB_WIDTH_2X;
 		*active_speed = IB_SPEED_HDR;

drivers/infiniband/hw/mlx5/qp.c

@@ -3729,6 +3729,7 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 	} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
 		struct mlx5_ib_modify_qp_resp resp = {};
+		u32 out[MLX5_ST_SZ_DW(create_dct_out)] = {0};
 		u32 min_resp_len = offsetof(typeof(resp), dctn) +
 				   sizeof(resp.dctn);
 
@@ -3747,7 +3748,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		MLX5_SET(dctc, dctc, hop_limit, attr->ah_attr.grh.hop_limit);
 
 		err = mlx5_core_create_dct(dev->mdev, &qp->dct.mdct, qp->dct.in,
-					   MLX5_ST_SZ_BYTES(create_dct_in));
+					   MLX5_ST_SZ_BYTES(create_dct_in), out,
+					   sizeof(out));
 		if (err)
 			return err;
 		resp.dctn = qp->dct.mdct.mqp.qpn;

drivers/net/ethernet/mellanox/mlx5/core/qp.c

@@ -40,6 +40,9 @@
 #include "mlx5_core.h"
 #include "lib/eq.h"
 
+static int mlx5_core_drain_dct(struct mlx5_core_dev *dev,
+			       struct mlx5_core_dct *dct);
+
 static struct mlx5_core_rsc_common *
 mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn)
 {
@@ -227,20 +230,49 @@ static void destroy_resource_common(struct mlx5_core_dev *dev,
 	wait_for_completion(&qp->common.free);
 }
 
+static int _mlx5_core_destroy_dct(struct mlx5_core_dev *dev,
+				  struct mlx5_core_dct *dct, bool need_cleanup)
+{
+	u32 out[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
+	struct mlx5_core_qp *qp = &dct->mqp;
+	int err;
+
+	err = mlx5_core_drain_dct(dev, dct);
+	if (err) {
+		if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+			goto destroy;
+		} else {
+			mlx5_core_warn(
+				dev, "failed drain DCT 0x%x with error 0x%x\n",
+				qp->qpn, err);
+			return err;
+		}
+	}
+	wait_for_completion(&dct->drained);
+destroy:
+	if (need_cleanup)
+		destroy_resource_common(dev, &dct->mqp);
+	MLX5_SET(destroy_dct_in, in, opcode, MLX5_CMD_OP_DESTROY_DCT);
+	MLX5_SET(destroy_dct_in, in, dctn, qp->qpn);
+	MLX5_SET(destroy_dct_in, in, uid, qp->uid);
+	err = mlx5_cmd_exec(dev, (void *)&in, sizeof(in),
+			    (void *)&out, sizeof(out));
+	return err;
+}
+
 int mlx5_core_create_dct(struct mlx5_core_dev *dev,
 			 struct mlx5_core_dct *dct,
-			 u32 *in, int inlen)
+			 u32 *in, int inlen,
+			 u32 *out, int outlen)
 {
-	u32 out[MLX5_ST_SZ_DW(create_dct_out)]   = {0};
-	u32 din[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
-	u32 dout[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
 	struct mlx5_core_qp *qp = &dct->mqp;
 	int err;
 
 	init_completion(&dct->drained);
 	MLX5_SET(create_dct_in, in, opcode, MLX5_CMD_OP_CREATE_DCT);
 
-	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
+	err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
 	if (err) {
 		mlx5_core_warn(dev, "create DCT failed, ret %d\n", err);
 		return err;
@@ -254,11 +286,7 @@ int mlx5_core_create_dct(struct mlx5_core_dev *dev,
 
 	return 0;
 err_cmd:
-	MLX5_SET(destroy_dct_in, din, opcode, MLX5_CMD_OP_DESTROY_DCT);
+	_mlx5_core_destroy_dct(dev, dct, false);
-	MLX5_SET(destroy_dct_in, din, dctn, qp->qpn);
-	MLX5_SET(destroy_dct_in, din, uid, qp->uid);
-	mlx5_cmd_exec(dev, (void *)&in, sizeof(din),
-		      (void *)&out, sizeof(dout));
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_core_create_dct);
@@ -323,29 +351,7 @@ static int mlx5_core_drain_dct(struct mlx5_core_dev *dev,
 int mlx5_core_destroy_dct(struct mlx5_core_dev *dev,
 			  struct mlx5_core_dct *dct)
 {
-	u32 out[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
+	return _mlx5_core_destroy_dct(dev, dct, true);
-	u32 in[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
-	struct mlx5_core_qp *qp = &dct->mqp;
-	int err;
-
-	err = mlx5_core_drain_dct(dev, dct);
-	if (err) {
-		if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-			goto destroy;
-		} else {
-			mlx5_core_warn(dev, "failed drain DCT 0x%x with error 0x%x\n", qp->qpn, err);
-			return err;
-		}
-	}
-	wait_for_completion(&dct->drained);
-destroy:
-	destroy_resource_common(dev, &dct->mqp);
-	MLX5_SET(destroy_dct_in, in, opcode, MLX5_CMD_OP_DESTROY_DCT);
-	MLX5_SET(destroy_dct_in, in, dctn, qp->qpn);
-	MLX5_SET(destroy_dct_in, in, uid, qp->uid);
-	err = mlx5_cmd_exec(dev, (void *)&in, sizeof(in),
-			    (void *)&out, sizeof(out));
-	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_core_destroy_dct);
 

include/linux/mlx5/qp.h

@@ -557,7 +557,8 @@ static inline struct mlx5_core_mkey *__mlx5_mr_lookup(struct mlx5_core_dev *dev,
 
 int mlx5_core_create_dct(struct mlx5_core_dev *dev,
 			 struct mlx5_core_dct *qp,
-			 u32 *in, int inlen);
+			 u32 *in, int inlen,
+			 u32 *out, int outlen);
 int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 			struct mlx5_core_qp *qp,
 			u32 *in,