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

Pull rdma updates from Jason Gunthorpe:

 - Various minor code cleanups and fixes for hns, iser, cxgb4, hfi1,
   rxe, erdma, mana_ib

 - Prefetch supprot for rxe ODP

 - Remove memory window support from hns as new device FW is no longer
   support it

 - Remove qib, it is very old and obsolete now, Cornelis wishes to
   restructure the hfi1/qib shared layer

 - Fix a race in destroying CQs where we can still end up with work
   running because the work is cancled before the driver stops
   triggering it

 - Improve interaction with namespaces:
     * Follow the devlink namespace for newly spawned RDMA devices
     * Create iopoib net devces in the parent IB device's namespace
     * Allow CAP_NET_RAW checks to pass in user namespaces

 - A new flow control scheme for IB MADs to try and avoid queue
   overflows in the network

 - Fix 2G message sizes in bnxt_re

 - Optimize mkey layout for mlx5 DMABUF

 - New "DMA Handle" concept to allow controlling PCI TPH and steering
   tags

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (71 commits)
  RDMA/siw: Change maintainer email address
  RDMA/mana_ib: add support of multiple ports
  RDMA/mlx5: Refactor optional counters steering code
  RDMA/mlx5: Add DMAH support for reg_user_mr/reg_user_dmabuf_mr
  IB: Extend UVERBS_METHOD_REG_MR to get DMAH
  RDMA/mlx5: Add DMAH object support
  RDMA/core: Introduce a DMAH object and its alloc/free APIs
  IB/core: Add UVERBS_METHOD_REG_MR on the MR object
  net/mlx5: Add support for device steering tag
  net/mlx5: Expose IFC bits for TPH
  PCI/TPH: Expose pcie_tph_get_st_table_size()
  RDMA/mlx5: Fix incorrect MKEY masking
  RDMA/mlx5: Fix returned type from _mlx5r_umr_zap_mkey()
  RDMA/mlx5: remove redundant check on err on return expression
  RDMA/mana_ib: add additional port counters
  RDMA/mana_ib: Fix DSCP value in modify QP
  RDMA/efa: Add CQ with external memory support
  RDMA/core: Add umem "is_contiguous" and "start_dma_addr" helpers
  RDMA/uverbs: Add a common way to create CQ with umem
  RDMA/mlx5: Optimize DMABUF mkey page size
  ...

1 files changed, 45 insertions, 2 deletions

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index d4263385850a..3145cb34a1d2 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -145,6 +145,33 @@ bool rdma_dev_access_netns(const struct ib_device *dev, const struct net *net)
 }
 EXPORT_SYMBOL(rdma_dev_access_netns);
 
+/**
+ * rdma_dev_has_raw_cap() - Returns whether a specified rdma device has
+ *			    CAP_NET_RAW capability or not.
+ *
+ * @dev:	Pointer to rdma device whose capability to be checked
+ *
+ * Returns true if a rdma device's owning user namespace has CAP_NET_RAW
+ * capability, otherwise false. When rdma subsystem is in legacy shared network,
+ * namespace mode, the default net namespace is considered.
+ */
+bool rdma_dev_has_raw_cap(const struct ib_device *dev)
+{
+	const struct net *net;
+
+	/* Network namespace is the resource whose user namespace
+	 * to be considered. When in shared mode, there is no reliable
+	 * network namespace resource, so consider the default net namespace.
+	 */
+	if (ib_devices_shared_netns)
+		net = &init_net;
+	else
+		net = read_pnet(&dev->coredev.rdma_net);
+
+	return ns_capable(net->user_ns, CAP_NET_RAW);
+}
+EXPORT_SYMBOL(rdma_dev_has_raw_cap);
+
 /*
  * xarray has this behavior where it won't iterate over NULL values stored in
  * allocated arrays.  So we need our own iterator to see all values stored in
@@ -557,6 +584,8 @@ static void rdma_init_coredev(struct ib_core_device *coredev,
 /**
  * _ib_alloc_device - allocate an IB device struct
  * @size:size of structure to allocate
+ * @net: network namespace device should be located in, namespace
+ *       must stay valid until ib_register_device() is completed.
  *
  * Low-level drivers should use ib_alloc_device() to allocate &struct
  * ib_device.  @size is the size of the structure to be allocated,
@@ -564,7 +593,7 @@ static void rdma_init_coredev(struct ib_core_device *coredev,
  * ib_dealloc_device() must be used to free structures allocated with
  * ib_alloc_device().
  */
-struct ib_device *_ib_alloc_device(size_t size)
+struct ib_device *_ib_alloc_device(size_t size, struct net *net)
 {
 	struct ib_device *device;
 	unsigned int i;
@@ -581,7 +610,15 @@ struct ib_device *_ib_alloc_device(size_t size)
 		return NULL;
 	}
 
-	rdma_init_coredev(&device->coredev, device, &init_net);
+	/* ib_devices_shared_netns can't change while we have active namespaces
+	 * in the system which means either init_net is passed or the user has
+	 * no idea what they are doing.
+	 *
+	 * To avoid breaking backward compatibility, when in shared mode,
+	 * force to init the device in the init_net.
+	 */
+	net = ib_devices_shared_netns ? &init_net : net;
+	rdma_init_coredev(&device->coredev, device, net);
 
 	INIT_LIST_HEAD(&device->event_handler_list);
 	spin_lock_init(&device->qp_open_list_lock);
@@ -2671,6 +2708,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, add_sub_dev);
 	SET_DEVICE_OP(dev_ops, advise_mr);
 	SET_DEVICE_OP(dev_ops, alloc_dm);
+	SET_DEVICE_OP(dev_ops, alloc_dmah);
 	SET_DEVICE_OP(dev_ops, alloc_hw_device_stats);
 	SET_DEVICE_OP(dev_ops, alloc_hw_port_stats);
 	SET_DEVICE_OP(dev_ops, alloc_mr);
@@ -2691,6 +2729,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, create_ah);
 	SET_DEVICE_OP(dev_ops, create_counters);
 	SET_DEVICE_OP(dev_ops, create_cq);
+	SET_DEVICE_OP(dev_ops, create_cq_umem);
 	SET_DEVICE_OP(dev_ops, create_flow);
 	SET_DEVICE_OP(dev_ops, create_qp);
 	SET_DEVICE_OP(dev_ops, create_rwq_ind_table);
@@ -2698,6 +2737,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, create_user_ah);
 	SET_DEVICE_OP(dev_ops, create_wq);
 	SET_DEVICE_OP(dev_ops, dealloc_dm);
+	SET_DEVICE_OP(dev_ops, dealloc_dmah);
 	SET_DEVICE_OP(dev_ops, dealloc_driver);
 	SET_DEVICE_OP(dev_ops, dealloc_mw);
 	SET_DEVICE_OP(dev_ops, dealloc_pd);
@@ -2763,8 +2803,10 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, modify_srq);
 	SET_DEVICE_OP(dev_ops, modify_wq);
 	SET_DEVICE_OP(dev_ops, peek_cq);
+	SET_DEVICE_OP(dev_ops, pre_destroy_cq);
 	SET_DEVICE_OP(dev_ops, poll_cq);
 	SET_DEVICE_OP(dev_ops, port_groups);
+	SET_DEVICE_OP(dev_ops, post_destroy_cq);
 	SET_DEVICE_OP(dev_ops, post_recv);
 	SET_DEVICE_OP(dev_ops, post_send);
 	SET_DEVICE_OP(dev_ops, post_srq_recv);
@@ -2793,6 +2835,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_OBJ_SIZE(dev_ops, ib_ah);
 	SET_OBJ_SIZE(dev_ops, ib_counters);
 	SET_OBJ_SIZE(dev_ops, ib_cq);
+	SET_OBJ_SIZE(dev_ops, ib_dmah);
 	SET_OBJ_SIZE(dev_ops, ib_mw);
 	SET_OBJ_SIZE(dev_ops, ib_pd);
 	SET_OBJ_SIZE(dev_ops, ib_qp);