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

Pull Mellanox rdma updates from Doug Ledford:
 "Mellanox specific updates for 4.11 merge window

  Because the Mellanox code required being based on a net-next tree, I
  keept it separate from the remainder of the RDMA stack submission that
  is based on 4.10-rc3.

  This branch contains:

   - Various mlx4 and mlx5 fixes and minor changes

   - Support for adding a tag match rule to flow specs

   - Support for cvlan offload operation for raw ethernet QPs

   - A change to the core IB code to recognize raw eth capabilities and
     enumerate them (touches non-Mellanox code)

   - Implicit On-Demand Paging memory registration support"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (40 commits)
  IB/mlx5: Fix configuration of port capabilities
  IB/mlx4: Take source GID by index from HW GID table
  IB/mlx5: Fix blue flame buffer size calculation
  IB/mlx4: Remove unused variable from function declaration
  IB: Query ports via the core instead of direct into the driver
  IB: Add protocol for USNIC
  IB/mlx4: Support raw packet protocol
  IB/mlx5: Support raw packet protocol
  IB/core: Add raw packet protocol
  IB/mlx5: Add implicit MR support
  IB/mlx5: Expose MR cache for mlx5_ib
  IB/mlx5: Add null_mkey access
  IB/umem: Indicate that process is being terminated
  IB/umem: Update on demand page (ODP) support
  IB/core: Add implicit MR flag
  IB/mlx5: Support creation of a WQ with scatter FCS offload
  IB/mlx5: Enable QP creation with cvlan offload
  IB/mlx5: Enable WQ creation and modification with cvlan offload
  IB/mlx5: Expose vlan offloads capabilities
  IB/uverbs: Enable QP creation with cvlan offload
  ...

5 files changed, 149 insertions, 21 deletions

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 4609b921f899..446b56a5260b 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -99,9 +99,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	if (dmasync)
 		dma_attrs |= DMA_ATTR_WRITE_BARRIER;
 
-	if (!size)
-		return ERR_PTR(-EINVAL);
-
 	/*
 	 * If the combination of the addr and size requested for this memory
 	 * region causes an integer overflow, return error.
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 6b079a31dced..f2fc0431512d 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -239,6 +239,71 @@ static const struct mmu_notifier_ops ib_umem_notifiers = {
 	.invalidate_range_end       = ib_umem_notifier_invalidate_range_end,
 };
 
+struct ib_umem *ib_alloc_odp_umem(struct ib_ucontext *context,
+				  unsigned long addr,
+				  size_t size)
+{
+	struct ib_umem *umem;
+	struct ib_umem_odp *odp_data;
+	int pages = size >> PAGE_SHIFT;
+	int ret;
+
+	umem = kzalloc(sizeof(*umem), GFP_KERNEL);
+	if (!umem)
+		return ERR_PTR(-ENOMEM);
+
+	umem->context   = context;
+	umem->length    = size;
+	umem->address   = addr;
+	umem->page_size = PAGE_SIZE;
+	umem->writable  = 1;
+
+	odp_data = kzalloc(sizeof(*odp_data), GFP_KERNEL);
+	if (!odp_data) {
+		ret = -ENOMEM;
+		goto out_umem;
+	}
+	odp_data->umem = umem;
+
+	mutex_init(&odp_data->umem_mutex);
+	init_completion(&odp_data->notifier_completion);
+
+	odp_data->page_list = vzalloc(pages * sizeof(*odp_data->page_list));
+	if (!odp_data->page_list) {
+		ret = -ENOMEM;
+		goto out_odp_data;
+	}
+
+	odp_data->dma_list = vzalloc(pages * sizeof(*odp_data->dma_list));
+	if (!odp_data->dma_list) {
+		ret = -ENOMEM;
+		goto out_page_list;
+	}
+
+	down_write(&context->umem_rwsem);
+	context->odp_mrs_count++;
+	rbt_ib_umem_insert(&odp_data->interval_tree, &context->umem_tree);
+	if (likely(!atomic_read(&context->notifier_count)))
+		odp_data->mn_counters_active = true;
+	else
+		list_add(&odp_data->no_private_counters,
+			 &context->no_private_counters);
+	up_write(&context->umem_rwsem);
+
+	umem->odp_data = odp_data;
+
+	return umem;
+
+out_page_list:
+	vfree(odp_data->page_list);
+out_odp_data:
+	kfree(odp_data);
+out_umem:
+	kfree(umem);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL(ib_alloc_odp_umem);
+
 int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem)
 {
 	int ret_val;
@@ -270,18 +335,20 @@ int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem)
 
 	init_completion(&umem->odp_data->notifier_completion);
 
-	umem->odp_data->page_list = vzalloc(ib_umem_num_pages(umem) *
+	if (ib_umem_num_pages(umem)) {
+		umem->odp_data->page_list = vzalloc(ib_umem_num_pages(umem) *
 					    sizeof(*umem->odp_data->page_list));
-	if (!umem->odp_data->page_list) {
-		ret_val = -ENOMEM;
-		goto out_odp_data;
-	}
+		if (!umem->odp_data->page_list) {
+			ret_val = -ENOMEM;
+			goto out_odp_data;
+		}
 
-	umem->odp_data->dma_list = vzalloc(ib_umem_num_pages(umem) *
+		umem->odp_data->dma_list = vzalloc(ib_umem_num_pages(umem) *
 					  sizeof(*umem->odp_data->dma_list));
-	if (!umem->odp_data->dma_list) {
-		ret_val = -ENOMEM;
-		goto out_page_list;
+		if (!umem->odp_data->dma_list) {
+			ret_val = -ENOMEM;
+			goto out_page_list;
+		}
 	}
 
 	/*
@@ -466,6 +533,7 @@ static int ib_umem_odp_map_dma_single_page(
 		}
 		umem->odp_data->dma_list[page_index] = dma_addr | access_mask;
 		umem->odp_data->page_list[page_index] = page;
+		umem->npages++;
 		stored_page = 1;
 	} else if (umem->odp_data->page_list[page_index] == page) {
 		umem->odp_data->dma_list[page_index] |= access_mask;
@@ -505,7 +573,8 @@ out:
  * for failure.
  * An -EAGAIN error code is returned when a concurrent mmu notifier prevents
  * the function from completing its task.
- *
+ * An -ENOENT error code indicates that userspace process is being terminated
+ * and mm was already destroyed.
  * @umem: the umem to map and pin
  * @user_virt: the address from which we need to map.
  * @bcnt: the minimal number of bytes to pin and map. The mapping might be
@@ -553,7 +622,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 
 	owning_mm = get_task_mm(owning_process);
 	if (owning_mm == NULL) {
-		ret = -EINVAL;
+		ret = -ENOENT;
 		goto out_put_task;
 	}
 
@@ -665,6 +734,7 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
 				put_page(page);
 			umem->odp_data->page_list[idx] = NULL;
 			umem->odp_data->dma_list[idx] = 0;
+			umem->npages--;
 		}
 	}
 	mutex_unlock(&umem->odp_data->umem_mutex);
diff --git a/drivers/infiniband/core/umem_rbtree.c b/drivers/infiniband/core/umem_rbtree.c
index 727d788448f5..d176597b4d78 100644
--- a/drivers/infiniband/core/umem_rbtree.c
+++ b/drivers/infiniband/core/umem_rbtree.c
@@ -78,17 +78,32 @@ int rbt_ib_umem_for_each_in_range(struct rb_root *root,
 				  void *cookie)
 {
 	int ret_val = 0;
-	struct umem_odp_node *node;
+	struct umem_odp_node *node, *next;
 	struct ib_umem_odp *umem;
 
 	if (unlikely(start == last))
 		return ret_val;
 
-	for (node = rbt_ib_umem_iter_first(root, start, last - 1); node;
-			node = rbt_ib_umem_iter_next(node, start, last - 1)) {
+	for (node = rbt_ib_umem_iter_first(root, start, last - 1);
+			node; node = next) {
+		next = rbt_ib_umem_iter_next(node, start, last - 1);
 		umem = container_of(node, struct ib_umem_odp, interval_tree);
 		ret_val = cb(umem->umem, start, last, cookie) || ret_val;
 	}
 
 	return ret_val;
 }
+EXPORT_SYMBOL(rbt_ib_umem_for_each_in_range);
+
+struct ib_umem_odp *rbt_ib_umem_lookup(struct rb_root *root,
+				       u64 addr, u64 length)
+{
+	struct umem_odp_node *node;
+
+	node = rbt_ib_umem_iter_first(root, addr, addr + length - 1);
+	if (node)
+		return container_of(node, struct ib_umem_odp, interval_tree);
+	return NULL;
+
+}
+EXPORT_SYMBOL(rbt_ib_umem_lookup);
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 455034ac994e..e1bedf0bac04 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -228,6 +228,7 @@ struct ib_uverbs_flow_spec {
 		struct ib_uverbs_flow_spec_ipv4    ipv4;
 		struct ib_uverbs_flow_spec_tcp_udp tcp_udp;
 		struct ib_uverbs_flow_spec_ipv6    ipv6;
+		struct ib_uverbs_flow_spec_action_tag	flow_tag;
 	};
 };
 
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 700782203483..b4b395a054ac 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1891,7 +1891,8 @@ static int create_qp(struct ib_uverbs_file *file,
 				IB_QP_CREATE_CROSS_CHANNEL |
 				IB_QP_CREATE_MANAGED_SEND |
 				IB_QP_CREATE_MANAGED_RECV |
-				IB_QP_CREATE_SCATTER_FCS)) {
+				IB_QP_CREATE_SCATTER_FCS |
+				IB_QP_CREATE_CVLAN_STRIPPING)) {
 		ret = -EINVAL;
 		goto err_put;
 	}
@@ -3143,6 +3144,25 @@ out_put:
 	return ret ? ret : in_len;
 }
 
+static int kern_spec_to_ib_spec_action(struct ib_uverbs_flow_spec *kern_spec,
+				       union ib_flow_spec *ib_spec)
+{
+	ib_spec->type = kern_spec->type;
+	switch (ib_spec->type) {
+	case IB_FLOW_SPEC_ACTION_TAG:
+		if (kern_spec->flow_tag.size !=
+		    sizeof(struct ib_uverbs_flow_spec_action_tag))
+			return -EINVAL;
+
+		ib_spec->flow_tag.size = sizeof(struct ib_flow_spec_action_tag);
+		ib_spec->flow_tag.tag_id = kern_spec->flow_tag.tag_id;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static size_t kern_spec_filter_sz(struct ib_uverbs_flow_spec_hdr *spec)
 {
 	/* Returns user space filter size, includes padding */
@@ -3167,8 +3187,8 @@ static ssize_t spec_filter_size(void *kern_spec_filter, u16 kern_filter_size,
 	return kern_filter_size;
 }
 
-static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
-				union ib_flow_spec *ib_spec)
+static int kern_spec_to_ib_spec_filter(struct ib_uverbs_flow_spec *kern_spec,
+				       union ib_flow_spec *ib_spec)
 {
 	ssize_t actual_filter_sz;
 	ssize_t kern_filter_sz;
@@ -3263,6 +3283,18 @@ static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
 	return 0;
 }
 
+static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
+				union ib_flow_spec *ib_spec)
+{
+	if (kern_spec->reserved)
+		return -EINVAL;
+
+	if (kern_spec->type >= IB_FLOW_SPEC_ACTION_TAG)
+		return kern_spec_to_ib_spec_action(kern_spec, ib_spec);
+	else
+		return kern_spec_to_ib_spec_filter(kern_spec, ib_spec);
+}
+
 int ib_uverbs_ex_create_wq(struct ib_uverbs_file *file,
 			   struct ib_device *ib_dev,
 			   struct ib_udata *ucore,
@@ -3325,6 +3357,9 @@ int ib_uverbs_ex_create_wq(struct ib_uverbs_file *file,
 	wq_init_attr.wq_context = file;
 	wq_init_attr.wq_type = cmd.wq_type;
 	wq_init_attr.event_handler = ib_uverbs_wq_event_handler;
+	if (ucore->inlen >= (offsetof(typeof(cmd), create_flags) +
+			     sizeof(cmd.create_flags)))
+		wq_init_attr.create_flags = cmd.create_flags;
 	obj->uevent.events_reported = 0;
 	INIT_LIST_HEAD(&obj->uevent.event_list);
 	wq = pd->device->create_wq(pd, &wq_init_attr, uhw);
@@ -3480,7 +3515,7 @@ int ib_uverbs_ex_modify_wq(struct ib_uverbs_file *file,
 	if (!cmd.attr_mask)
 		return -EINVAL;
 
-	if (cmd.attr_mask > (IB_WQ_STATE | IB_WQ_CUR_STATE))
+	if (cmd.attr_mask > (IB_WQ_STATE | IB_WQ_CUR_STATE | IB_WQ_FLAGS))
 		return -EINVAL;
 
 	wq = idr_read_wq(cmd.wq_handle, file->ucontext);
@@ -3489,6 +3524,10 @@ int ib_uverbs_ex_modify_wq(struct ib_uverbs_file *file,
 
 	wq_attr.curr_wq_state = cmd.curr_wq_state;
 	wq_attr.wq_state = cmd.wq_state;
+	if (cmd.attr_mask & IB_WQ_FLAGS) {
+		wq_attr.flags = cmd.flags;
+		wq_attr.flags_mask = cmd.flags_mask;
+	}
 	ret = wq->device->modify_wq(wq, &wq_attr, cmd.attr_mask, uhw);
 	put_wq_read(wq);
 	return ret;
@@ -4323,6 +4362,12 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 
 	resp.max_wq_type_rq = attr.max_wq_type_rq;
 	resp.response_length += sizeof(resp.max_wq_type_rq);
+
+	if (ucore->outlen < resp.response_length + sizeof(resp.raw_packet_caps))
+		goto end;
+
+	resp.raw_packet_caps = attr.raw_packet_caps;
+	resp.response_length += sizeof(resp.raw_packet_caps);
 end:
 	err = ib_copy_to_udata(ucore, &resp, resp.response_length);
 	return err;