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

Pull rdma fixes from Jason Gunthorpe:
 "A mixture of small bug fixes and a small security issue:

   - WARN_ON when IPoIB is automatically moved between namespaces

   - Long standing bug where mlx5 would use the wrong page for the
     doorbell recovery memory if fork is used

   - Security fix for mlx4 that disables the timestamp feature

   - Several crashers for mlx5

   - Plug a recent mlx5 memory leak for the sig_mr"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  IB/mlx5: Fix initializing CQ fragments buffer
  RDMA/mlx5: Delete right entry from MR signature database
  RDMA: Verify port when creating flow rule
  RDMA/mlx5: Block FDB rules when not in switchdev mode
  RDMA/mlx4: Do not map the core_clock page to user space unless enabled
  RDMA/mlx5: Use different doorbell memory for different processes
  RDMA/ipoib: Fix warning caused by destroying non-initial netns

Author: torvalds

drivers/infiniband/core/uverbs_cmd.c

@@ -3248,6 +3248,11 @@ static int ib_uverbs_ex_create_flow(struct uverbs_attr_bundle *attrs)
 		goto err_free_attr;
 	}
 
+	if (!rdma_is_port_valid(uobj->context->device, cmd.flow_attr.port)) {
+		err = -EINVAL;
+		goto err_uobj;
+	}
+
 	qp = uobj_get_obj_read(qp, UVERBS_OBJECT_QP, cmd.qp_handle, attrs);
 	if (!qp) {
 		err = -EINVAL;

drivers/infiniband/hw/mlx4/main.c

@@ -581,12 +581,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->cq_caps.max_cq_moderation_count = MLX4_MAX_CQ_COUNT;
 	props->cq_caps.max_cq_moderation_period = MLX4_MAX_CQ_PERIOD;
 
-	if (!mlx4_is_slave(dev->dev))
-		err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
-
 	if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) {
 		resp.response_length += sizeof(resp.hca_core_clock_offset);
-		if (!err && !mlx4_is_slave(dev->dev)) {
+		if (!mlx4_get_internal_clock_params(dev->dev, &clock_params)) {
 			resp.comp_mask |= MLX4_IB_QUERY_DEV_RESP_MASK_CORE_CLOCK_OFFSET;
 			resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
 		}
@@ -1702,9 +1699,6 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 	struct mlx4_dev *dev = (to_mdev(qp->device))->dev;
 	int is_bonded = mlx4_is_bonded(dev);
 
-	if (!rdma_is_port_valid(qp->device, flow_attr->port))
-		return ERR_PTR(-EINVAL);
-
 	if (flow_attr->flags & ~IB_FLOW_ATTR_FLAGS_DONT_TRAP)
 		return ERR_PTR(-EOPNOTSUPP);
 

drivers/infiniband/hw/mlx5/cq.c

@@ -849,15 +849,14 @@ static void destroy_cq_user(struct mlx5_ib_cq *cq, struct ib_udata *udata)
 	ib_umem_release(cq->buf.umem);
 }
 
-static void init_cq_frag_buf(struct mlx5_ib_cq *cq,
-			     struct mlx5_ib_cq_buf *buf)
+static void init_cq_frag_buf(struct mlx5_ib_cq_buf *buf)
 {
 	int i;
 	void *cqe;
 	struct mlx5_cqe64 *cqe64;
 
 	for (i = 0; i < buf->nent; i++) {
-		cqe = get_cqe(cq, i);
+		cqe = mlx5_frag_buf_get_wqe(&buf->fbc, i);
 		cqe64 = buf->cqe_size == 64 ? cqe : cqe + 64;
 		cqe64->op_own = MLX5_CQE_INVALID << 4;
 	}
@@ -883,7 +882,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
 	if (err)
 		goto err_db;
 
-	init_cq_frag_buf(cq, &cq->buf);
+	init_cq_frag_buf(&cq->buf);
 
 	*inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
 		 MLX5_FLD_SZ_BYTES(create_cq_in, pas[0]) *
@@ -1184,7 +1183,7 @@ static int resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
 	if (err)
 		goto ex;
 
-	init_cq_frag_buf(cq, cq->resize_buf);
+	init_cq_frag_buf(cq->resize_buf);
 
 	return 0;
 

drivers/infiniband/hw/mlx5/doorbell.c

@@ -41,6 +41,7 @@ struct mlx5_ib_user_db_page {
 	struct ib_umem	       *umem;
 	unsigned long		user_virt;
 	int			refcnt;
+	struct mm_struct	*mm;
 };
 
 int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context,
@@ -53,7 +54,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context,
 	mutex_lock(&context->db_page_mutex);
 
 	list_for_each_entry(page, &context->db_page_list, list)
-		if (page->user_virt == (virt & PAGE_MASK))
+		if ((current->mm == page->mm) &&
+		    (page->user_virt == (virt & PAGE_MASK)))
 			goto found;
 
 	page = kmalloc(sizeof(*page), GFP_KERNEL);
@@ -71,6 +73,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context,
 		kfree(page);
 		goto out;
 	}
+	mmgrab(current->mm);
+	page->mm = current->mm;
 
 	list_add(&page->list, &context->db_page_list);
 
@@ -91,6 +95,7 @@ void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db)
 
 	if (!--db->u.user_page->refcnt) {
 		list_del(&db->u.user_page->list);
+		mmdrop(db->u.user_page->mm);
 		ib_umem_release(db->u.user_page->umem);
 		kfree(db->u.user_page);
 	}

drivers/infiniband/hw/mlx5/fs.c

@@ -1194,9 +1194,8 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 		goto free_ucmd;
 	}
 
-	if (flow_attr->port > dev->num_ports ||
-	    (flow_attr->flags &
-	     ~(IB_FLOW_ATTR_FLAGS_DONT_TRAP | IB_FLOW_ATTR_FLAGS_EGRESS))) {
+	if (flow_attr->flags &
+	    ~(IB_FLOW_ATTR_FLAGS_DONT_TRAP | IB_FLOW_ATTR_FLAGS_EGRESS)) {
 		err = -EINVAL;
 		goto free_ucmd;
 	}
@@ -2134,6 +2133,12 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_MATCHER_CREATE)(
 	if (err)
 		goto end;
 
+	if (obj->ns_type == MLX5_FLOW_NAMESPACE_FDB &&
+	    mlx5_eswitch_mode(dev->mdev) != MLX5_ESWITCH_OFFLOADS) {
+		err = -EINVAL;
+		goto end;
+	}
+
 	uobj->object = obj;
 	obj->mdev = dev->mdev;
 	atomic_set(&obj->usecnt, 0);

drivers/infiniband/hw/mlx5/mr.c

@@ -1940,8 +1940,8 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
 		mlx5r_deref_wait_odp_mkey(&mr->mmkey);
 
 	if (ibmr->type == IB_MR_TYPE_INTEGRITY) {
-		xa_cmpxchg(&dev->sig_mrs, mlx5_base_mkey(mr->mmkey.key), ibmr,
-			   NULL, GFP_KERNEL);
+		xa_cmpxchg(&dev->sig_mrs, mlx5_base_mkey(mr->mmkey.key),
+			   mr->sig, NULL, GFP_KERNEL);
 
 		if (mr->mtt_mr) {
 			rc = mlx5_ib_dereg_mr(&mr->mtt_mr->ibmr, NULL);

drivers/infiniband/ulp/ipoib/ipoib_netlink.c

@@ -163,6 +163,7 @@ static size_t ipoib_get_size(const struct net_device *dev)
 
 static struct rtnl_link_ops ipoib_link_ops __read_mostly = {
 	.kind		= "ipoib",
+	.netns_refund   = true,
 	.maxtype	= IFLA_IPOIB_MAX,
 	.policy		= ipoib_policy,
 	.priv_size	= sizeof(struct ipoib_dev_priv),

drivers/net/ethernet/mellanox/mlx4/fw.c

@@ -823,6 +823,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET		0xb0
 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET	0xa8
 #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET	0xac
+#define QUERY_DEV_CAP_MAP_CLOCK_TO_USER 0xc1
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET	0xcc
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET	0xd0
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET	0xd2
@@ -841,6 +842,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 
 	if (mlx4_is_mfunc(dev))
 		disable_unsupported_roce_caps(outbox);
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAP_CLOCK_TO_USER);
+	dev_cap->map_clock_to_user = field & 0x80;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_QP_OFFSET);
 	dev_cap->reserved_qps = 1 << (field & 0xf);
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_QP_OFFSET);

drivers/net/ethernet/mellanox/mlx4/fw.h

@@ -131,6 +131,7 @@ struct mlx4_dev_cap {
 	u32 health_buffer_addrs;
 	struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
 	bool wol_port[MLX4_MAX_PORTS + 1];
+	bool map_clock_to_user;
 };
 
 struct mlx4_func_cap {

drivers/net/ethernet/mellanox/mlx4/main.c

@@ -498,6 +498,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		}
 	}
 
+	dev->caps.map_clock_to_user  = dev_cap->map_clock_to_user;
 	dev->caps.uar_page_size	     = PAGE_SIZE;
 	dev->caps.num_uars	     = dev_cap->uar_size / PAGE_SIZE;
 	dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay;
@@ -1948,6 +1949,11 @@ int mlx4_get_internal_clock_params(struct mlx4_dev *dev,
 	if (mlx4_is_slave(dev))
 		return -EOPNOTSUPP;
 
+	if (!dev->caps.map_clock_to_user) {
+		mlx4_dbg(dev, "Map clock to user is not supported.\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (!params)
 		return -EINVAL;