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

Pull inifiniband/rdma updates from Doug Ledford:
 "This is a fairly sizeable set of changes.  I've put them through a
  decent amount of testing prior to sending the pull request due to
  that.

  There are still a few fixups that I know are coming, but I wanted to
  go ahead and get the big, sizable chunk into your hands sooner rather
  than waiting for those last few fixups.

  Of note is the fact that this creates what is intended to be a
  temporary area in the drivers/staging tree specifically for some
  cleanups and additions that are coming for the RDMA stack.  We
  deprecated two drivers (ipath and amso1100) and are waiting to hear
  back if we can deprecate another one (ehca).  We also put Intel's new
  hfi1 driver into this area because it needs to be refactored and a
  transfer library created out of the factored out code, and then it and
  the qib driver and the soft-roce driver should all be modified to use
  that library.

  I expect drivers/staging/rdma to be around for three or four kernel
  releases and then to go away as all of the work is completed and final
  deletions of deprecated drivers are done.

  Summary of changes for 4.3:

   - Create drivers/staging/rdma
   - Move amso1100 driver to staging/rdma and schedule for deletion
   - Move ipath driver to staging/rdma and schedule for deletion
   - Add hfi1 driver to staging/rdma and set TODO for move to regular
     tree
   - Initial support for namespaces to be used on RDMA devices
   - Add RoCE GID table handling to the RDMA core caching code
   - Infrastructure to support handling of devices with differing read
     and write scatter gather capabilities
   - Various iSER updates
   - Kill off unsafe usage of global mr registrations
   - Update SRP driver
   - Misc  mlx4 driver updates
   - Support for the mr_alloc verb
   - Support for a netlink interface between kernel and user space cache
     daemon to speed path record queries and route resolution
   - Ininitial support for safe hot removal of verbs devices"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (136 commits)
  IB/ipoib: Suppress warning for send only join failures
  IB/ipoib: Clean up send-only multicast joins
  IB/srp: Fix possible protection fault
  IB/core: Move SM class defines from ib_mad.h to ib_smi.h
  IB/core: Remove unnecessary defines from ib_mad.h
  IB/hfi1: Add PSM2 user space header to header_install
  IB/hfi1: Add CSRs for CONFIG_SDMA_VERBOSITY
  mlx5: Fix incorrect wc pkey_index assignment for GSI messages
  IB/mlx5: avoid destroying a NULL mr in reg_user_mr error flow
  IB/uverbs: reject invalid or unknown opcodes
  IB/cxgb4: Fix if statement in pick_local_ip6adddrs
  IB/sa: Fix rdma netlink message flags
  IB/ucma: HW Device hot-removal support
  IB/mlx4_ib: Disassociate support
  IB/uverbs: Enable device removal when there are active user space applications
  IB/uverbs: Explicitly pass ib_dev to uverbs commands
  IB/uverbs: Fix race between ib_uverbs_open and remove_one
  IB/uverbs: Fix reference counting usage of event files
  IB/core: Make ib_dealloc_pd return void
  IB/srp: Create an insecure all physical rkey only if needed
  ...

1 files changed, 78 insertions, 53 deletions

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 30eb245..e1f2c98 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -213,28 +213,79 @@ EXPORT_SYMBOL(rdma_port_get_link_layer);
 
 /* Protection domains */
 
+/**
+ * ib_alloc_pd - Allocates an unused protection domain.
+ * @device: The device on which to allocate the protection domain.
+ *
+ * A protection domain object provides an association between QPs, shared
+ * receive queues, address handles, memory regions, and memory windows.
+ *
+ * Every PD has a local_dma_lkey which can be used as the lkey value for local
+ * memory operations.
+ */
 struct ib_pd *ib_alloc_pd(struct ib_device *device)
 {
 	struct ib_pd *pd;
+	struct ib_device_attr devattr;
+	int rc;
+
+	rc = ib_query_device(device, &devattr);
+	if (rc)
+		return ERR_PTR(rc);
 
 	pd = device->alloc_pd(device, NULL, NULL);
+	if (IS_ERR(pd))
+		return pd;
+
+	pd->device = device;
+	pd->uobject = NULL;
+	pd->local_mr = NULL;
+	atomic_set(&pd->usecnt, 0);
+
+	if (devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)
+		pd->local_dma_lkey = device->local_dma_lkey;
+	else {
+		struct ib_mr *mr;
+
+		mr = ib_get_dma_mr(pd, IB_ACCESS_LOCAL_WRITE);
+		if (IS_ERR(mr)) {
+			ib_dealloc_pd(pd);
+			return (struct ib_pd *)mr;
+		}
 
-	if (!IS_ERR(pd)) {
-		pd->device  = device;
-		pd->uobject = NULL;
-		atomic_set(&pd->usecnt, 0);
+		pd->local_mr = mr;
+		pd->local_dma_lkey = pd->local_mr->lkey;
 	}
-
 	return pd;
 }
 EXPORT_SYMBOL(ib_alloc_pd);
 
-int ib_dealloc_pd(struct ib_pd *pd)
+/**
+ * ib_dealloc_pd - Deallocates a protection domain.
+ * @pd: The protection domain to deallocate.
+ *
+ * It is an error to call this function while any resources in the pd still
+ * exist.  The caller is responsible to synchronously destroy them and
+ * guarantee no new allocations will happen.
+ */
+void ib_dealloc_pd(struct ib_pd *pd)
 {
-	if (atomic_read(&pd->usecnt))
-		return -EBUSY;
+	int ret;
+
+	if (pd->local_mr) {
+		ret = ib_dereg_mr(pd->local_mr);
+		WARN_ON(ret);
+		pd->local_mr = NULL;
+	}
 
-	return pd->device->dealloc_pd(pd);
+	/* uverbs manipulates usecnt with proper locking, while the kabi
+	   requires the caller to guarantee we can't race here. */
+	WARN_ON(atomic_read(&pd->usecnt));
+
+	/* Making delalloc_pd a void return is a WIP, no driver should return
+	   an error here. */
+	ret = pd->device->dealloc_pd(pd);
+	WARN_ONCE(ret, "Infiniband HW driver failed dealloc_pd");
 }
 EXPORT_SYMBOL(ib_dealloc_pd);
 
@@ -1168,54 +1219,28 @@ int ib_dereg_mr(struct ib_mr *mr)
 }
 EXPORT_SYMBOL(ib_dereg_mr);
 
-struct ib_mr *ib_create_mr(struct ib_pd *pd,
-			   struct ib_mr_init_attr *mr_init_attr)
-{
-	struct ib_mr *mr;
-
-	if (!pd->device->create_mr)
-		return ERR_PTR(-ENOSYS);
-
-	mr = pd->device->create_mr(pd, mr_init_attr);
-
-	if (!IS_ERR(mr)) {
-		mr->device  = pd->device;
-		mr->pd      = pd;
-		mr->uobject = NULL;
-		atomic_inc(&pd->usecnt);
-		atomic_set(&mr->usecnt, 0);
-	}
-
-	return mr;
-}
-EXPORT_SYMBOL(ib_create_mr);
-
-int ib_destroy_mr(struct ib_mr *mr)
-{
-	struct ib_pd *pd;
-	int ret;
-
-	if (atomic_read(&mr->usecnt))
-		return -EBUSY;
-
-	pd = mr->pd;
-	ret = mr->device->destroy_mr(mr);
-	if (!ret)
-		atomic_dec(&pd->usecnt);
-
-	return ret;
-}
-EXPORT_SYMBOL(ib_destroy_mr);
-
-struct ib_mr *ib_alloc_fast_reg_mr(struct ib_pd *pd, int max_page_list_len)
+/**
+ * ib_alloc_mr() - Allocates a memory region
+ * @pd:            protection domain associated with the region
+ * @mr_type:       memory region type
+ * @max_num_sg:    maximum sg entries available for registration.
+ *
+ * Notes:
+ * Memory registeration page/sg lists must not exceed max_num_sg.
+ * For mr_type IB_MR_TYPE_MEM_REG, the total length cannot exceed
+ * max_num_sg * used_page_size.
+ *
+ */
+struct ib_mr *ib_alloc_mr(struct ib_pd *pd,
+			  enum ib_mr_type mr_type,
+			  u32 max_num_sg)
 {
 	struct ib_mr *mr;
 
-	if (!pd->device->alloc_fast_reg_mr)
+	if (!pd->device->alloc_mr)
 		return ERR_PTR(-ENOSYS);
 
-	mr = pd->device->alloc_fast_reg_mr(pd, max_page_list_len);
-
+	mr = pd->device->alloc_mr(pd, mr_type, max_num_sg);
 	if (!IS_ERR(mr)) {
 		mr->device  = pd->device;
 		mr->pd      = pd;
@@ -1226,7 +1251,7 @@ struct ib_mr *ib_alloc_fast_reg_mr(struct ib_pd *pd, int max_page_list_len)
 
 	return mr;
 }
-EXPORT_SYMBOL(ib_alloc_fast_reg_mr);
+EXPORT_SYMBOL(ib_alloc_mr);
 
 struct ib_fast_reg_page_list *ib_alloc_fast_reg_page_list(struct ib_device *device,
 							  int max_page_list_len)